© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25332
    Prev
    Next
    INDEX
    Explanations

    code/scientific papers

    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
    è¿Ļ对
    -0.30
     nóng
    -0.27
     gray
    -0.25
    \brief
    -0.24
     parentNode
    -0.24
    çĪ¶åŃIJ
    -0.24
    adora
    -0.24
     Papers
    -0.24
    ä¸įå®ļ
    -0.23
    åĨįåĪ°
    -0.23
    POSITIVE LOGITS
    everyone
    0.27
     rubbed
    0.25
    åĬ¡
    0.25
    Everyone
    0.25
    idden
    0.25
    gebung
    0.25
     unconditional
    0.24
    ç»Ļä½łä»¬
    0.23
    alan
    0.23
    OU
    0.23
    Activations Density 0.007%

    No Known Activations