© 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. 97983
    Prev
    Next
    INDEX
    Explanations

    Questions and conditionals

    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
    virt
    -0.29
    allel
    -0.27
     amateurs
    -0.24
     commentator
    -0.24
    chemes
    -0.23
    /colors
    -0.23
     kidding
    -0.23
    è¿ĻéĩĮæĺ¯
    -0.23
     depart
    -0.23
    »
    -0.23
    POSITIVE LOGITS
     Would
    0.38
     would
    0.35
    Would
    0.32
    ä¼ļ
    0.31
    would
    0.30
    ä¼ļéĢīæĭ©
    0.30
     würde
    0.28
    ä¼ļåıijçĶŁ
    0.28
    ä»ĸä¼ļ
    0.27
    æľĥ
    0.27
    Activations Density 0.008%

    No Known Activations