© 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. 88163
    Prev
    Next
    INDEX
    Explanations

    Different, multiple, variety

    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
    že
    -0.26
    hydr
    -0.25
    æĥħ绪
    -0.25
    æ»ļ
    -0.25
    æĸ¹ä½į
    -0.25
    ยะ
    -0.25
    æ³½
    -0.24
    avel
    -0.24
    essential
    -0.24
    ĻĤ
    -0.23
    POSITIVE LOGITS
    ouch
    0.28
     sprung
    0.23
     å¤
    0.23
    led
    0.23
     probe
    0.23
     Probe
    0.23
    lot
    0.23
    iche
    0.23
    stras
    0.23
    æľ¬ç«Ļ
    0.23
    Activations Density 0.007%

    No Known Activations