© 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. 112200
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    çIJ¶
    -0.26
    ä¾®
    -0.26
    åıijå¸ĥæŶéĹ´
    -0.26
    åı·åı¬
    -0.25
    æ¯ķç«Łæĺ¯
    -0.25
    true
    -0.25
    第ä¸Ģå±Ĭ
    -0.24
    è°°
    -0.24
     quoi
    -0.23
    åIJ¸å¼ķæĽ´å¤ļ
    -0.23
    POSITIVE LOGITS
    inge
    0.31
    erea
    0.26
    REW
    0.25
    erview
    0.25
    SO
    0.24
     Lobby
    0.23
     Siege
    0.23
    oden
    0.23
    ammers
    0.23
    ioned
    0.23
    Activations Density 0.000%

    No Known Activations