© 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. 129815
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    mere
    -0.27
    èĻļæĭŁ
    -0.26
    =_("
    -0.25
    ä»ħä»ħ
    -0.24
    lein
    -0.24
    à¤ł
    -0.24
    .deploy
    -0.24
    è¾¼
    -0.24
     slic
    -0.23
    æ²ĺ
    -0.23
    POSITIVE LOGITS
    æ°¸ä¹ħ
    0.28
    åĩºåħ¥
    0.27
    igel
    0.24
    第ä¸Ģ个
    0.24
     Adj
    0.24
    å¾Īéĩįè¦ģ
    0.24
    ีà¹Ī
    0.24
    ä¸Ĭä¸ĭ
    0.23
    æĽ´è¦ģ
    0.23
    è¿ĺè¦ģ
    0.23
    Activations Density 0.006%

    No Known Activations