© 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. 129827
    Prev
    Next
    INDEX
    Explanations

    code/math/random strings

    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
    好äºĨ
    -0.30
    åĨľåī¯
    -0.25
    äºĨå¾Īå¤ļ
    -0.25
    äºĨä¸įå°ij
    -0.25
    .makeText
    -0.24
    ersen
    -0.24
    ;++
    -0.24
    éħ¤
    -0.24
    uries
    -0.24
    åĨľåī¯äº§åĵģ
    -0.24
    POSITIVE LOGITS
     tuần
    0.30
     pon
    0.28
    otas
    0.27
    éĶģ
    0.27
     tutorial
    0.26
    gest
    0.26
     se
    0.26
    ich
    0.25
    æ´Ľåħĭ
    0.25
    onic
    0.25
    Activations Density 0.021%

    No Known Activations