© 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. 87551
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    æĪij们å°Ĩ
    -0.26
    ç»ĻæĪij们
    -0.25
     pole
    -0.25
     rdr
    -0.24
    å·¥å§Ķ
    -0.24
    åºı
    -0.24
    oint
    -0.24
    è¿Ļç¯ĩæĸĩç«ł
    -0.24
    åĿŀ
    -0.24
    -loss
    -0.23
    POSITIVE LOGITS
    should
    0.27
    osals
    0.25
    @property
    0.24
    å¸Į
    0.23
    abouts
    0.23
     }</
    0.23
    _requirements
    0.23
    ót
    0.23
    åĽ°
    0.23
    hips
    0.22
    Activations Density 0.313%

    No Known Activations