© 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. 98346
    Prev
    Next
    INDEX
    Explanations

    Starts with Z

    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
    ector
    -0.27
    åĿĢ
    -0.26
    sey
    -0.24
    ä¸ĭæĿ¥çļĦ
    -0.24
    è¾İ
    -0.24
    ä¸ĭä¾Ĩ
    -0.23
    aceous
    -0.23
    åģ¥åº·äº§ä¸ļ
    -0.22
     middle
    -0.22
    Resources
    -0.22
    POSITIVE LOGITS
    pered
    0.34
    ahlen
    0.29
    illions
    0.27
     hå
    0.27
     Encore
    0.27
    å·¥ä¸ļ大åѦ
    0.27
    ombie
    0.27
     Matth
    0.26
    ephir
    0.25
    (z
    0.25
    Activations Density 0.292%

    No Known Activations