© 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. 88504
    Prev
    Next
    INDEX
    Explanations

    Abstract language

    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
    edin
    -0.27
    并å°Ĩ
    -0.25
    metro
    -0.25
    orks
    -0.24
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.24
    iatrics
    -0.24
     careful
    -0.24
    並å°ĩ
    -0.24
    icts
    -0.23
     Friendly
    -0.23
    POSITIVE LOGITS
    æİł
    0.29
    è·ij
    0.28
    æŀĦéĢł
    0.27
    åįı
    0.27
    å·´å·´
    0.25
     repr
    0.25
    æĹłæ³ķ
    0.25
    ä¸įåIJĪçIJĨ
    0.25
     unavailable
    0.24
    umba
    0.24
    Activations Density 0.003%

    No Known Activations