© 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. 33-TRANSCODER-HP
    7. 53144
    Prev
    Next
    INDEX
    Explanations

    advertising campaigns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Province
    -0.28
    è´¢åĬ¡
    -0.27
    ctrine
    -0.26
    æĶ¿åºľ
    -0.26
    Canonical
    -0.26
    èĪĨ论
    -0.25
    abies
    -0.25
     fy
    -0.25
    .banner
    -0.25
    Financial
    -0.24
    POSITIVE LOGITS
    add
    0.35
     plugs
    0.35
     add
    0.34
     plug
    0.31
     perm
    0.29
    Add
    0.28
     McDon
    0.28
     tÃŃch
    0.27
     integrated
    0.26
     programming
    0.26
    Activations Density 0.069%

    No Known Activations