© 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. 40270
    Prev
    Next
    INDEX
    Explanations

    Code and Licenses

    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
     occupy
    -0.27
    DH
    -0.27
    SR
    -0.26
    èĤĥ
    -0.26
     ÑģкоÑĢо
    -0.25
    Former
    -0.25
     Proble
    -0.25
    PW
    -0.25
     pict
    -0.25
     impro
    -0.25
    POSITIVE LOGITS
    ienen
    0.34
    oyal
    0.32
    ién
    0.31
    ailed
    0.31
    illed
    0.31
    ours
    0.31
    ateful
    0.30
    iel
    0.30
    ãĥĥãĤ°
    0.30
    arn
    0.30
    Activations Density 0.123%

    No Known Activations