© 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. 108208
    Prev
    Next
    INDEX
    Explanations

    across

    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
    çłĶ究éĻ¢
    -0.26
     Alley
    -0.26
    iena
    -0.25
    æİ¢
    -0.25
     Mellon
    -0.24
    cket
    -0.24
    椿
    -0.24
    æį¢æĿ¥
    -0.23
    çľĭæľĽ
    -0.23
    éĽĨä¸Ńåľ¨
    -0.23
    POSITIVE LOGITS
     activity
    0.30
     strong
    0.29
     trunc
    0.28
     insights
    0.28
     sol
    0.28
    ÐļÑĥÑĢÑģ
    0.27
     ant
    0.27
     ga
    0.27
     path
    0.27
     a
    0.26
    Activations Density 0.937%

    No Known Activations