© 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. 27-TRANSCODER-HP
    7. 9141
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Camden
    -0.29
     accelerator
    -0.29
     realpath
    -0.26
    鸢
    -0.26
    ;y
    -0.24
    camel
    -0.24
     ter
    -0.24
    æĻºèĥ½åĮĸ
    -0.24
     aperture
    -0.23
    .scene
    -0.23
    POSITIVE LOGITS
    éĽĨåĽ¢èĤ¡ä»½
    0.29
    atsu
    0.27
    oki
    0.27
    åİĭå®ŀ
    0.25
    æŀķ头
    0.25
    主è¦ģéĽĨä¸Ń
    0.24
    åħļå·¥å§Ķ
    0.24
    hra
    0.23
    责任åĪ¶
    0.23
    èĢķ
    0.23
    Activations Density 0.009%

    No Known Activations