© 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. 53315
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    å¸Ń
    -0.30
    ben
    -0.28
     gamm
    -0.26
    å±Ī
    -0.26
    fram
    -0.25
    contr
    -0.25
    æ´½
    -0.25
    ulating
    -0.25
     criter
    -0.25
    orting
    -0.24
    POSITIVE LOGITS
    欢åij¼
    0.25
    mitter
    0.25
     Off
    0.25
     sino
    0.24
     magnet
    0.24
     addObject
    0.24
    pirit
    0.24
    pire
    0.24
    ×ŀ×Ļת
    0.23
    cross
    0.23
    Activations Density 0.017%

    No Known Activations