© 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. 41077
    Prev
    Next
    INDEX
    Explanations

    resisting an urge

    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
    供电公司
    -0.07
     resolve
    -0.07
    ATEG
    -0.07
    <!--↵
    -0.07
    DEPEND
    -0.07
     (?,
    -0.06
    ↭
    -0.06
    诛
    -0.06
     ApplicationUser
    -0.06
    価
    -0.06
    POSITIVE LOGITS
     Assessment
    0.07
    >Hello
    0.07
     Toby
    0.07
    Intro
    0.07
    $app
    0.07
    indrome
    0.07
     Brock
    0.07
    .dom
    0.07
    distance
    0.07
     comfortably
    0.07
    Activations Density 0.053%

    No Known Activations