© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24022
    Prev
    Next
    INDEX
    Explanations

    Angela

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tower
    -0.27
    ients
    -0.26
     ending
    -0.25
    entimes
    -0.25
    çĸ²
    -0.24
    etch
    -0.24
    letics
    -0.24
    }//
    -0.24
    æĻļ
    -0.23
    çŃ¾åŃĹ
    -0.23
    POSITIVE LOGITS
    è¿Ļ家
    0.32
     TRY
    0.27
    稳æŃ¥æİ¨è¿Ľ
    0.27
    ÕĬ
    0.26
     Salad
    0.26
    è¿Ļ个è¡Įä¸ļ
    0.25
    efs
    0.25
    ozy
    0.25
    rv
    0.25
    èĮĦåŃIJ
    0.25
    Activations Density 0.003%

    No Known Activations