© 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. 15-RESID-POST-AA
    11. 13543
    Prev
    Next
    INDEX
    Explanations

    risk levels

    np_max-act · gemini-2.0-flash

    sentences or phrases that reassure by stating that risks (especially health/environmental) are low or not significant.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARM
    -0.07
    ㏂
    -0.07
    𬬹
    -0.07
    _db
    -0.07
    ^n
    -0.07
    锕
    -0.06
    让你
    -0.06
    stitute
    -0.06
    ⚒
    -0.06
     tiêu
    -0.06
    POSITIVE LOGITS
    (policy
    0.07
    Recently
    0.07
    ראל
    0.07
    _pose
    0.07
    _SORT
    0.07
     SPACE
    0.07
     Wend
    0.07
    _Pre
    0.07
     onFinish
    0.07
    的信任
    0.07
    Activations Density 0.104%

    No Known Activations