© 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. 39062
    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
    è¡Ĺ
    -0.27
     \`
    -0.25
     CORE
    -0.25
    жа
    -0.25
    æĭĵ
    -0.24
     (`
    -0.24
     Codable
    -0.24
     GBP
    -0.24
    -functional
    -0.24
    çĽİ
    -0.24
    POSITIVE LOGITS
     force
    0.28
     notice
    0.27
     burial
    0.25
    iento
    0.25
     funeral
    0.24
     viewType
    0.24
    ISIBLE
    0.24
    .seek
    0.24
     reality
    0.23
     noexcept
    0.23
    Activations Density 0.183%

    No Known Activations

    This feature has no known activations.