© 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. 39789
    Prev
    Next
    INDEX
    Explanations

    m

    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
    obbies
    -0.29
    abo
    -0.29
    ROC
    -0.28
    echa
    -0.27
    shares
    -0.27
    OTS
    -0.26
    ibox
    -0.26
    lobs
    -0.25
    otty
    -0.25
    OTP
    -0.25
    POSITIVE LOGITS
    a
    0.50
    o
    0.38
    m
    0.32
    ī
    0.28
     ol
    0.27
    olar
    0.27
    os
    0.27
     parenthesis
    0.26
     evolve
    0.26
     m
    0.26
    Activations Density 8.145%

    No Known Activations