© 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. 112703
    Prev
    Next
    INDEX
    Explanations

    Showing information

    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
    å·¥èīº
    -0.24
    çĪ¸çĪ¸
    -0.24
    old
    -0.24
    eur
    -0.23
    åĮ»èį¯
    -0.23
    exter
    -0.23
    %'
    -0.23
    æĪĸèĢħ说
    -0.23
    å¢ĻéĿ¢
    -0.23
    åĮ»ç§ij
    -0.23
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.28
    olvable
    0.26
    entin
    0.26
    inium
    0.26
    éĸī
    0.25
     treadmill
    0.25
    çľĭå¾Ĺ
    0.25
    è·¡
    0.25
    çļĩ家
    0.24
     ABOVE
    0.24
    Activations Density 0.014%

    No Known Activations