© 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. 19-RESID-POST-AA
    6. 69509
    Prev
    Next
    INDEX
    Explanations

    Computer code and fault tolerance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    كنيسة
    -0.07
     ROAD
    -0.07
    Gravity
    -0.07
    (':',
    -0.07
    ممارسة
    -0.07
     IX
    -0.06
    xDD
    -0.06
    珊
    -0.06
     المجال
    -0.06
     upto
    -0.06
    POSITIVE LOGITS
     Len
    0.08
     Bachelor
    0.07
     Example
    0.07
     Lexer
    0.07
    ;\
    0.07
     outfile
    0.07
     Manager
    0.07
    满意的
    0.07
     bro
    0.07
    &eacute
    0.06
    Activations Density 0.000%

    No Known Activations