© 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. 40048
    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
    ardy
    -0.26
    ware
    -0.25
    WARE
    -0.25
    amentals
    -0.25
    าว
    -0.24
    ãĤıãĤĬ
    -0.24
    SHOT
    -0.24
     Bund
    -0.24
    deen
    -0.24
    IXEL
    -0.23
    POSITIVE LOGITS
    åı·
    0.30
    otty
    0.29
    oot
    0.28
    otti
    0.26
    ooter
    0.26
    oo
    0.26
    ee
    0.25
    ott
    0.25
    -pocket
    0.25
    vio
    0.24
    Activations Density 0.017%

    No Known Activations