© 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. 108348
    Prev
    Next
    INDEX
    Explanations

    says

    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
    агенÑĤ
    -0.26
    acob
    -0.26
    éĻĦ
    -0.26
     Throwable
    -0.26
     Stitch
    -0.25
    æľĿ
    -0.24
    ych
    -0.24
    jiang
    -0.24
    ä¼ĺåĮĸ
    -0.24
    cdb
    -0.24
    POSITIVE LOGITS
    ç²Ĺç³Ļ
    0.29
    èĴĻ
    0.28
    IJľç´¢
    0.27
    çĶŁäº§çļĦ
    0.27
     Redistributions
    0.27
    emony
    0.27
    éľ²
    0.26
    æ¸ħæ¾Ī
    0.26
     evenings
    0.25
     dusty
    0.25
    Activations Density 0.147%

    No Known Activations