© 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. 54430
    Prev
    Next
    INDEX
    Explanations

    silver or gold

    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
    éĻ¢éĻ¢éķ¿
    -0.28
    ç³ĸ
    -0.28
     ZX
    -0.28
    canf
    -0.28
    éĻ¢åī¯éĻ¢éķ¿
    -0.27
    ?f
    -0.26
    cation
    -0.26
    atinum
    -0.25
    ocol
    -0.25
    antt
    -0.24
    POSITIVE LOGITS
     overlays
    0.31
     beats
    0.28
     clicks
    0.28
     overl
    0.27
     flagged
    0.27
     flashed
    0.26
     hurdles
    0.26
    etes
    0.26
     flashes
    0.26
    Unnamed
    0.25
    Activations Density 0.010%

    No Known Activations