© 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. 98249
    Prev
    Next
    INDEX
    Explanations

    image

    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
     himself
    -0.27
    ·»
    -0.25
    ç»ĨåĪĨ
    -0.24
     Dir
    -0.24
    åĽ¢è´Ń
    -0.24
    elled
    -0.24
     @@
    -0.24
    æĶĢçĻ»
    -0.23
    —he
    -0.23
    toa
    -0.23
    POSITIVE LOGITS
    pios
    0.26
    ç«ĭ马
    0.25
    <!--↵
    0.24
    	IL
    0.24
    ä½ķåĨµ
    0.24
    STA
    0.24
    quals
    0.24
    rotein
    0.24
    /il
    0.24
    液
    0.24
    Activations Density 0.008%

    No Known Activations