© 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. 2035
    Prev
    Next
    INDEX
    Explanations

    day

    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_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
     themselves
    -0.07
    .Copy
    -0.07
     pause
    -0.06
     JR
    -0.06
    ope
    -0.06
     Independence
    -0.06
    .Hide
    -0.06
    裾
    -0.06
    (null
    -0.06
    졸
    -0.06
    POSITIVE LOGITS
    trying
    0.08
     décembre
    0.07
     Persistent
    0.07
     Edison
    0.07
    הוראות
    0.06
    🤛
    0.06
    pta
    0.06
     vigilant
    0.06
     ROUT
    0.06
     grop
    0.06
    Activations Density 0.011%

    No Known Activations