© 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. 40293
    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
    æģĥ
    -0.26
    è¿Ļ个éĹ®é¢ĺ
    -0.26
     withdrawn
    -0.24
    DN
    -0.24
    ç°ª
    -0.24
     withdraw
    -0.24
    ún
    -0.23
     pen
    -0.23
    ripp
    -0.23
    çİ·
    -0.23
    POSITIVE LOGITS
     coaster
    0.27
    .until
    0.26
    éĻª
    0.26
    здание
    0.26
    _tE
    0.26
     taxa
    0.25
    红线
    0.24
     instantaneous
    0.24
    kah
    0.23
    èµŃ
    0.23
    Activations Density 0.051%

    No Known Activations

    This feature has no known activations.