© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87556
    Prev
    Next
    INDEX
    Explanations

    the

    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
    INUE
    -0.07
    (back
    -0.07
     "("
    -0.07
    /disable
    -0.07
     sharks
    -0.07
     barriers
    -0.07
     chicago
    -0.07
    欧阳
    -0.06
     CORE
    -0.06
    减值
    -0.06
    POSITIVE LOGITS
    еньк
    0.07
     recebe
    0.07
    极高
    0.07
    טבח
    0.07
    .oc
    0.07
     immediately
    0.07
    �件
    0.07
    ervers
    0.07
    �
    0.07
    된다
    0.07
    Activations Density 0.148%

    No Known Activations