© 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. 41807
    Prev
    Next
    INDEX
    Explanations

    Presiding over events

    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
    โช
    -0.07
    乃
    -0.07
     tốt
    -0.07
    镇江
    -0.07
    第一节
    -0.07
     güne
    -0.07
    >'+
    -0.07
    Գ
    -0.06
    还可
    -0.06
    findBy
    -0.06
    POSITIVE LOGITS
     Brasil
    0.08
     República
    0.08
     Moderator
    0.07
     Expo
    0.07
     interviewer
    0.07
    質量
    0.07
    -running
    0.07
     produto
    0.07
     COMPANY
    0.07
     Elder
    0.07
    Activations Density 0.004%

    No Known Activations