© 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. 97448
    Prev
    Next
    INDEX
    Explanations

    diseases

    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¿ħè¦ģ
    -0.27
    æķĻèĤ²èµĦæºIJ
    -0.26
     kiÅŁ
    -0.25
    oland
    -0.24
    æŀ«
    -0.24
    bai
    -0.24
    æľŁæľĽ
    -0.23
    åĩĨå¤ĩå·¥ä½ľ
    -0.23
     Experiment
    -0.22
    åĴĮå®ĮåĸĦ
    -0.22
    POSITIVE LOGITS
    Studies
    0.26
    latin
    0.26
    Tau
    0.25
    chluss
    0.24
    å§Ĭ妹
    0.23
    å©¿
    0.23
     fundamentally
    0.22
    ivet
    0.22
    INCT
    0.22
     (
    0.22
    Activations Density 0.015%

    No Known Activations