© 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. 25502
    Prev
    Next
    INDEX
    Explanations

    not

    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
    Negative Logits
     vit
    -0.28
    è§Ĵ
    -0.25
    ITES
    -0.25
     prerequisite
    -0.25
    rip
    -0.25
    ä¹ĭå¿ĥ
    -0.25
    éĢļ讯
    -0.25
    缴
    -0.24
    angu
    -0.24
    导èĩ´
    -0.24
    POSITIVE LOGITS
    æĭ£
    0.28
    ä¸įå¦Ĥ
    0.27
    æĭ¿èµ·
    0.25
    //-----------------------------------------------------------------------------↵
    0.24
    çĸ£
    0.24
    è¿ĺæľīä»Ģä¹Ī
    0.24
    è¥Ł
    0.24
    ä¸įæľį
    0.24
    ä¸įåıĬ
    0.24
    enie
    0.24
    Activations Density 0.002%

    No Known Activations