© 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. 129768
    Prev
    Next
    INDEX
    Explanations

    MA

    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
    igar
    -0.36
    egree
    -0.28
    /dat
    -0.28
    incoming
    -0.27
    æĭ¥æĬ±
    -0.25
     Banks
    -0.25
    -root
    -0.25
    itä
    -0.25
    iefs
    -0.25
    è¿Ļ个æĹ¶ä»£
    -0.25
    POSITIVE LOGITS
    ç½ķ
    0.28
    æļĤ
    0.28
    LEncoder
    0.27
     thÆ°á»Ŀng
    0.26
    åIJįä¹ī
    0.25
     setC
    0.25
    )?$
    0.24
     proven
    0.24
    ноÑģ
    0.24
     constructs
    0.24
    Activations Density 0.021%

    No Known Activations