© 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. 54212
    Prev
    Next
    INDEX
    Explanations

    in

    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
    assignments
    -0.26
    ertility
    -0.25
    .backends
    -0.25
    å½ĵäºĭ
    -0.24
    è°Ī
    -0.23
    gether
    -0.23
    çŁ¥
    -0.23
    çŃĨ
    -0.23
     pe
    -0.23
    JOR
    -0.23
    POSITIVE LOGITS
    ocket
    0.28
     ench
    0.26
    unsafe
    0.26
    -corner
    0.25
     sloppy
    0.25
     synced
    0.24
     oats
    0.24
    ä¸Ģæ³¢
    0.24
    -ch
    0.24
    ch
    0.24
    Activations Density 0.004%

    No Known Activations