© 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. 89825
    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
    rup
    -0.28
    ede
    -0.27
    MU
    -0.26
    dü
    -0.26
     Baghd
    -0.25
    éĩįä¸Ń
    -0.25
    æݥ轨
    -0.24
    andra
    -0.24
    ename
    -0.24
    身å¿ĥåģ¥åº·
    -0.24
    POSITIVE LOGITS
    acement
    0.31
    acements
    0.26
    /ac
    0.25
    éĵİ
    0.25
     {*}
    0.25
    ancellor
    0.24
     winners
    0.24
    rots
    0.24
     оп
    0.24
    -win
    0.24
    Activations Density 0.092%

    No Known Activations

    This feature has no known activations.