© 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. 25-TRANSCODER-HP
    7. 107357
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤ¬å´ĸ
    -0.29
    istle
    -0.27
    _comm
    -0.25
    çīĻ齿
    -0.24
    ahlen
    -0.24
    Vtbl
    -0.24
    轨迹
    -0.24
    éŀ£
    -0.23
    lope
    -0.23
    antes
    -0.23
    POSITIVE LOGITS
    ysi
    0.26
    妨
    0.24
     Tradable
    0.23
    åĽłä¸ºæĪij们
    0.23
     contributor
    0.23
    indent
    0.22
    onn
    0.22
    éĥ½ä¸įèĥ½
    0.22
    çľģæĶ¿åºľ
    0.22
    eenth
    0.22
    Activations Density 0.154%

    No Known Activations

    This feature has no known activations.