© 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. 35-TRANSCODER-HP
    7. 39545
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ķ
    -0.29
    .amazonaws
    -0.28
    为ä»Ģä¹Ī
    -0.27
    sher
    -0.27
    決
    -0.26
    åĪĨæĺİ
    -0.26
    åĨ³
    -0.24
    åıĸãĤĬ
    -0.24
    .ru
    -0.24
     Inf
    -0.24
    POSITIVE LOGITS
    èķī
    0.32
     SCN
    0.28
    CID
    0.27
    ampaign
    0.27
    äºĮèĢħ
    0.26
    ä¸Ģå¼Ģå§ĭå°±
    0.25
    achu
    0.25
    éĻIJéĩı
    0.25
     **/↵↵
    0.25
     setInterval
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.