© 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. 108156
    Prev
    Next
    INDEX
    Explanations

    movies

    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
     appeared
    -0.26
    .astype
    -0.26
     Zusammen
    -0.26
    æĿª
    -0.25
     Worst
    -0.25
    渲æŁĵ
    -0.25
    æ¶ĤæĬ¹
    -0.25
    线ä¸ĭ
    -0.25
    aid
    -0.24
    _IMPLEMENT
    -0.24
    POSITIVE LOGITS
    æİĤ
    0.30
    æ¯ı天éĥ½
    0.29
    unky
    0.26
    æĥ³çĿĢ
    0.25
    rogen
    0.25
    åĸĥ
    0.25
    veau
    0.25
     setLocation
    0.25
     rainbow
    0.24
    овÑĭй
    0.24
    Activations Density 0.916%

    No Known Activations