© 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. 22-TRANSCODER-HP
    7. 97764
    Prev
    Next
    INDEX
    Explanations

    online questions/discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -0.26
     ~~
    -0.26
     |_
    -0.25
    æŁIJç§į
    -0.25
    ized
    -0.25
    åĮĸçļĦ
    -0.24
    è¯ģ
    -0.24
     возд
    -0.23
    7
    -0.23
    Something
    -0.23
    POSITIVE LOGITS
    nah
    0.24
    usercontent
    0.24
    çĦ¶èĢĮ
    0.23
    çĿİ
    0.23
     capsule
    0.23
    swire
    0.23
     Pillow
    0.22
    iners
    0.22
    æ°ijèIJ¥ç»ıæµİ
    0.22
     Garn
    0.22
    Activations Density 0.010%

    No Known Activations