© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89581
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¢Ħæ¡Ī
    -0.30
    _TUN
    -0.25
    vi
    -0.25
    inci
    -0.25
    è¯Ĵ
    -0.25
    ви
    -0.24
    æĵIJ
    -0.24
     sanction
    -0.23
    è§Ī
    -0.23
     vi
    -0.23
    POSITIVE LOGITS
     Hubb
    0.29
    #ga
    0.28
    dimensions
    0.27
    oger
    0.26
    terr
    0.26
    elpers
    0.26
    prowadziÅĤ
    0.25
    Forget
    0.25
    itizer
    0.25
    bread
    0.25
    Activations Density 1.683%

    No Known Activations

    This feature has no known activations.