© 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. 41034
    Prev
    Next
    INDEX
    Explanations

    shapes being cut/clipped

    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
     classifiers
    -0.08
    破坏
    -0.07
    opper
    -0.07
     coff
    -0.07
     TRAIN
    -0.07
    .microsoft
    -0.07
     staffing
    -0.06
     millones
    -0.06
    ipp
    -0.06
    iff
    -0.06
    POSITIVE LOGITS
     Compared
    0.08
     english
    0.07
     BaseActivity
    0.07
     sacram
    0.07
     Km
    0.07
    Strategy
    0.06
     Москвы
    0.06
     argc
    0.06
    _reserved
    0.06
     Brid
    0.06
    Activations Density 0.033%

    No Known Activations