© 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. 107632
    Prev
    Next
    INDEX
    Explanations

    non-conversational text

    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
    eron
    -0.33
    åŃ
    -0.26
     TJ
    -0.26
     hab
    -0.25
     æĸ¹æ³ķ
    -0.25
    ethod
    -0.25
    è±ī
    -0.24
    éĻĮçĶŁ
    -0.24
    ç²¾ç¥ŀ
    -0.24
    inha
    -0.24
    POSITIVE LOGITS
    (bp
    0.28
     CPR
    0.26
    keys
    0.25
     Byron
    0.24
     Lif
    0.24
     BMI
    0.24
    ipline
    0.24
    uum
    0.24
    eltas
    0.24
     lif
    0.24
    Activations Density 0.904%

    No Known Activations