© 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. 89864
    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
    æĭĽå¾ħ
    -0.29
     cub
    -0.29
    ellig
    -0.27
     orth
    -0.26
    ê²Ł
    -0.26
    ORIZ
    -0.25
    ensity
    -0.25
     Sandwich
    -0.25
    orthy
    -0.25
    erate
    -0.25
    POSITIVE LOGITS
    ruise
    0.26
    æµ·æĭĶ
    0.25
    fsp
    0.25
    foil
    0.25
    ÑĩÑĥ
    0.24
    chein
    0.23
     Tester
    0.23
    ffa
    0.23
    LEEP
    0.23
    羣缸
    0.23
    Activations Density 2.426%

    No Known Activations

    This feature has no known activations.