© 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. 108955
    Prev
    Next
    INDEX
    Explanations

    technical instructions

    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
    loys
    -0.27
    standing
    -0.27
    desk
    -0.26
    amment
    -0.26
    tele
    -0.24
    quo
    -0.23
    .twig
    -0.23
    azen
    -0.23
    quer
    -0.23
    å°±è¶Ĭ
    -0.23
    POSITIVE LOGITS
    ä¸Ģ段æŶéĹ´
    0.76
     weeks
    0.74
    ä¸ī个æľĪ
    0.67
    å¤ļä¹ħ
    0.66
    åĩłå¤©
    0.66
     months
    0.66
    两个æľĪ
    0.64
    åįĬ个æľĪ
    0.63
    ä¸ī天
    0.62
     minutes
    0.60
    Activations Density 1.049%

    No Known Activations