© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30408
    Prev
    Next
    INDEX
    Explanations

    question answer pairs

    np_max-act · gemini-2.0-flash

    the special turn-boundary/end-of-message token (e.g., the <|im_end|> marker) indicating the end of a speaker's turn.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()-
    -0.07
    (Encoding
    -0.07
    诸如
    -0.07
    慷
    -0.07
     ברור
    -0.07
    ⌚
    -0.06
    .XPath
    -0.06
    <>
    -0.06
     directive
    -0.06
    툿
    -0.06
    POSITIVE LOGITS
     ears
    0.07
    一眼
    0.06
     vomiting
    0.06
    affe
    0.06
    权威
    0.06
    addOn
    0.06
    ன
    0.06
     shrinking
    0.06
     أ
    0.06
    Extreme
    0.06
    Activations Density 0.057%

    No Known Activations