© 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. 23-TRANSCODER-HP
    7. 24476
    Prev
    Next
    INDEX
    Explanations

    code, legal, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varied
    -0.28
    enses
    -0.27
     classics
    -0.26
    å½¹
    -0.26
     fundamentals
    -0.26
    ĸī
    -0.25
    ranges
    -0.25
    åĺ§
    -0.25
    å¤ļæł·åĮĸ
    -0.25
     Horn
    -0.24
    POSITIVE LOGITS
     drown
    0.27
     Able
    0.27
    æĸ°åħ´äº§ä¸ļ
    0.24
    æĻķ
    0.24
    OSH
    0.24
    osi
    0.24
     protector
    0.24
    ë³´íĺ¸
    0.23
    æ²»å®ī
    0.23
     sil
    0.23
    Activations Density 0.002%

    No Known Activations