© 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. 108173
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    DataExchange
    -0.30
    æİĪæĿĥ
    -0.29
    privileged
    -0.27
    .createNew
    -0.26
    iaz
    -0.26
    æİĪæ¬Ĭ
    -0.26
    产
    -0.26
     spontaneously
    -0.26
    寸
    -0.26
     consenting
    -0.25
    POSITIVE LOGITS
    è§Ħæł¼
    0.26
    èŁĭ
    0.26
    TimeInterval
    0.26
    çĶ¨æĿ¥
    0.26
     dred
    0.26
     fishes
    0.25
    çĤ®
    0.25
    .lines
    0.25
    [email
    0.25
    .lp
    0.25
    Activations Density 1.092%

    No Known Activations