© 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. 14-TRANSCODER-HP
    7. 41685
    Prev
    Next
    INDEX
    Explanations

    stories and tales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    izards
    -0.28
    osit
    -0.27
    ç¼İ
    -0.27
    èµĦ
    -0.25
    çį
    -0.25
    ç³Ł
    -0.25
    åľºéĿ¢
    -0.25
     Straw
    -0.25
    ç»
    -0.25
     ArrayAdapter
    -0.25
    POSITIVE LOGITS
     angle
    0.31
    Angle
    0.29
    thal
    0.29
    angle
    0.29
    OMATIC
    0.27
    lim
    0.27
     Angle
    0.26
    etsk
    0.26
    _REDIRECT
    0.26
    _secondary
    0.25
    Activations Density 0.084%

    No Known Activations