© 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. 39853
    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
     postage
    -0.31
    @(
    -0.29
     !_
    -0.28
     politique
    -0.28
    çī²
    -0.27
    å¾Ĺèµ·
    -0.26
    æĶ¯éħį
    -0.25
    -drop
    -0.24
    @foreach
    -0.24
    ä¸įå°ı
    -0.24
    POSITIVE LOGITS
    Terminal
    0.28
    _outputs
    0.27
    è¾ĵåĩº
    0.26
    UV
    0.25
    ully
    0.24
     proj
    0.24
    تأ
    0.24
     Dess
    0.24
     eff
    0.24
     Outputs
    0.24
    Activations Density 3.856%

    No Known Activations

    This feature has no known activations.