© 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. 39658
    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
    交æµģ
    -0.27
     record
    -0.24
     DECLARE
    -0.24
    GetInstance
    -0.24
    roc
    -0.23
    yk
    -0.23
    isco
    -0.23
    åĪ¹
    -0.23
    认è¯Ĩ
    -0.23
    åı¤åŁİ
    -0.23
    POSITIVE LOGITS
    oft
    0.26
    atab
    0.26
    HEN
    0.24
     denn
    0.24
     Tup
    0.24
     curs
    0.24
    она
    0.24
    Brains
    0.23
    uration
    0.23
    æªĢ
    0.23
    Activations Density 2.800%

    No Known Activations

    This feature has no known activations.