© 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. 25-TRANSCODER-HP
    7. 108899
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.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¢ĥ
    -0.26
    ä¸ĥ个
    -0.25
    Ñģ
    -0.25
    _dims
    -0.25
    ible
    -0.25
    ä»ĵ
    -0.25
    ük
    -0.25
    elig
    -0.24
    /nginx
    -0.24
    xee
    -0.24
    POSITIVE LOGITS
     Coff
    0.27
     Lancaster
    0.27
     Winston
    0.27
    åħ¶ä»ĸåĽ½å®¶
    0.26
    cord
    0.25
     licens
    0.25
    تÙĪر
    0.25
    cott
    0.25
    erton
    0.24
    æĽ´æ·±
    0.24
    Activations Density 0.905%

    No Known Activations