© 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. 40171
    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
    specific
    -0.26
    æ¯ı
    -0.25
    æ¯ıä¸Ģ个
    -0.24
     ItemType
    -0.24
    ####
    -0.24
    every
    -0.24
    kj
    -0.24
    llx
    -0.23
    æľ¬å±Ĭ
    -0.23
     colorful
    -0.23
    POSITIVE LOGITS
     Exec
    0.27
     sucks
    0.26
    seite
    0.25
    inese
    0.25
    inski
    0.24
    isci
    0.24
    .Xr
    0.24
    å¾ĺ
    0.24
    ocre
    0.23
    anko
    0.23
    Activations Density 1.403%

    No Known Activations

    This feature has no known activations.