© 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. 41013
    Prev
    Next
    INDEX
    Explanations

    some (in other languages)

    np_max-act · gemini-2.0-flash
    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
    .FONT
    -0.08
    ottie
    -0.08
    Ѫ
    -0.07
    unordered
    -0.07
    )};↵
    -0.07
    过度
    -0.07
     Performs
    -0.07
     concentr
    -0.07
    _LOGGER
    -0.07
    rots
    -0.07
    POSITIVE LOGITS
    KeyValuePair
    0.07
    被认为是
    0.07
    (jLabel
    0.07
    侍
    0.07
    .dgv
    0.07
    �
    0.07
    кал
    0.07
    ("
    0.07
    我们认为
    0.07
    	actual
    0.07
    Activations Density 0.014%

    No Known Activations