© 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. 112429
    Prev
    Next
    INDEX
    Explanations

    Hers

    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
    ëĵĿ
    -0.33
    æľĪ饼
    -0.27
    å¼Ń
    -0.25
    åħ¥ä½ı
    -0.25
    '-
    -0.25
    ç§
    -0.24
     complex
    -0.24
     Marian
    -0.24
    BTN
    -0.24
    履约
    -0.23
    POSITIVE LOGITS
     tagged
    0.28
    å°±è¿ij
    0.28
    è¯į
    0.28
    åĢ¾
    0.27
    nung
    0.26
    noun
    0.26
     Nero
    0.26
    è°ĭ
    0.25
    esseract
    0.24
     Connected
    0.24
    Activations Density 0.001%

    No Known Activations