© 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. 20-TRANSCODER-HP
    7. 64328
    Prev
    Next
    INDEX
    Explanations

    choices and options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»»ä½ķä¸Ģ个
    -0.38
    ä»»ä½ķ
    -0.36
    ä»»ä½ķæŶåĢĻ
    -0.35
    edly
    -0.34
    æĹłè®º
    -0.33
     any
    -0.32
     ANY
    -0.32
     imaginable
    -0.32
    ä¸į管
    -0.31
     dom
    -0.31
    POSITIVE LOGITS
    utan
    0.31
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.28
     more
    0.27
     More
    0.26
    _more
    0.25
    ict
    0.25
    é¦ĸ次
    0.24
    âĵĺ
    0.24
    >Delete
    0.24
     ATS
    0.24
    Activations Density 31.443%

    No Known Activations