© 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. 39044
    Prev
    Next
    INDEX
    Explanations

    Ex

    np_max-act-logits · gemini-2.0-flash
    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
     unfolding
    -0.36
     unfolded
    -0.36
    å±ķå¼Ģ
    -0.36
     unfold
    -0.33
    鹤
    -0.28
     excavation
    -0.28
     unfolds
    -0.28
    èĥĢ
    -0.27
    ìŀī
    -0.27
    å±ķ
    -0.26
    POSITIVE LOGITS
     An
    0.28
     Lost
    0.27
     Min
    0.26
    -widget
    0.26
     Aff
    0.26
     Surv
    0.26
    ao
    0.25
    uevo
    0.25
     an
    0.25
    in
    0.25
    Activations Density 0.167%

    No Known Activations