© 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. 89078
    Prev
    Next
    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    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
    浦
    -0.29
    non
    -0.27
     –
    -0.25
    clar
    -0.25
    PAR
    -0.25
    çĽ¸ä¿¡
    -0.25
     RP
    -0.25
    i
    -0.25
     ---------
    -0.25
     Rut
    -0.24
    POSITIVE LOGITS
    agrams
    0.29
     hilar
    0.27
     setInterval
    0.27
     grandchildren
    0.27
    -awesome
    0.26
    occo
    0.26
    NIC
    0.25
    ocaust
    0.25
    Sharper
    0.25
     createSelector
    0.25
    Activations Density 9.798%

    No Known Activations