© 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. 57718
    Prev
    Next
    INDEX
    Explanations

    down

    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
    æİī
    -0.42
    åĩºæĿ¥
    -0.40
    åĩºæĿ¥çļĦ
    -0.39
    åĩºä¾Ĩ
    -0.35
    èĢĮåĩº
    -0.35
    ä¸ĭæĿ¥
    -0.34
    æİīäºĨ
    -0.33
    å¼ĢæĿ¥
    -0.32
    åĩº
    -0.32
    åĩºåİ»
    -0.30
    POSITIVE LOGITS
    -tone
    0.28
     bitwise
    0.27
     permanently
    0.27
    -inf
    0.26
     stark
    0.25
    æļĹæļĹ
    0.25
    olt
    0.25
     nearby
    0.24
    -ton
    0.24
     adapt
    0.24
    Activations Density 0.056%

    No Known Activations