© 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. 30605
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     responsibility
    -0.07
    협
    -0.07
     Calif
    -0.07
    体现
    -0.07
     gele
    -0.07
    Master
    -0.06
    =null
    -0.06
     Became
    -0.06
    假
    -0.06
    大切
    -0.06
    POSITIVE LOGITS
    ivec
    0.07
    lyn
    0.07
    anzeigen
    0.07
     ayır
    0.07
     Spotify
    0.07
     בניית
    0.07
    kin
    0.06
    永不
    0.06
    verbosity
    0.06
    ossa
    0.06
    Activations Density 0.025%

    No Known Activations