© 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. 111365
    Prev
    Next
    INDEX
    Explanations

    you

    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
    ä¹Łæ¯Ķè¾ĥ
    -0.26
    è¿Ŀç«ł
    -0.26
     options
    -0.26
    å·¥ä½ľæķĪçİĩ
    -0.26
    就说
    -0.26
    èĢĥéªĮ
    -0.25
    å°Ĭ严
    -0.25
    æľįåĬ¡è´¨éĩı
    -0.25
    å·¥ä½ľäººåijĺ
    -0.25
    ä¸Ģç¢Ĺ
    -0.24
    POSITIVE LOGITS
     discontin
    0.29
    DisplayStyle
    0.26
    leigh
    0.25
    è½½ä½ĵ
    0.25
     rede
    0.25
    likely
    0.25
    å¿ħ
    0.25
     melee
    0.25
     occasion
    0.25
    oci
    0.24
    Activations Density 0.006%

    No Known Activations