© 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. 98228
    Prev
    Next
    INDEX
    Explanations

    stop

    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
    åīĥ
    -0.27
     Fit
    -0.26
     <<-
    -0.25
    辫
    -0.25
     Fitness
    -0.24
    çľ¼éķľ
    -0.24
    %%%%
    -0.24
    æ¹ľ
    -0.24
    lash
    -0.23
    _CLR
    -0.23
    POSITIVE LOGITS
    acular
    0.30
    åĪ°æĿ¥
    0.28
    ä¸Ĭä¼ł
    0.26
    ä»·æł¼ä¸Ĭ涨
    0.26
    åĮĸè¿Ľç¨ĭ
    0.26
    __$
    0.25
    EndInit
    0.25
    åĨįçĶŁ
    0.25
    rijk
    0.25
    à¹Īà¸Ńà¸Ļ
    0.24
    Activations Density 0.016%

    No Known Activations