© 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. 88632
    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
    åľ¨è¿ĻéĩĮ
    -0.29
    sw
    -0.28
     here
    -0.28
     wh
    -0.27
    am
    -0.27
    åľ¨çİ°åľº
    -0.26
    atures
    -0.26
    wh
    -0.26
    fra
    -0.26
    alam
    -0.25
    POSITIVE LOGITS
    æ®ĸ
    0.27
    çŁĽçĽ¾
    0.27
    VersionUID
    0.25
    .transition
    0.25
    æĿĤè´¨
    0.25
    ãĥ³
    0.25
    REST
    0.25
    çĶ·åŃ©
    0.24
    StdString
    0.24
    COPE
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.