© 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. 41513
    Prev
    Next
    INDEX
    Explanations

    illnesses

    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
    -reviewed
    -0.28
    locals
    -0.26
    è¯Ħ审
    -0.26
    åĨµ
    -0.26
     dese
    -0.26
    èĩªè§ī
    -0.25
    æĶ¯çº¿
    -0.25
    riot
    -0.25
     Bris
    -0.25
    éī´
    -0.25
    POSITIVE LOGITS
    _fit
    0.27
    ydro
    0.26
    ograms
    0.25
    :params
    0.25
    .labels
    0.24
    agrams
    0.24
    éĩįåŀĭ
    0.24
    åĨ·èĹı
    0.24
     Ãĸl
    0.24
    /language
    0.24
    Activations Density 0.194%

    No Known Activations