© 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. 25309
    Prev
    Next
    INDEX
    Explanations

    Source code

    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
     activity
    -0.29
     ydk
    -0.28
     assignable
    -0.28
     htmlentities
    -0.28
    æ´»åĬ¨
    -0.28
     HLS
    -0.27
    çľ¼åħī
    -0.27
    HEME
    -0.27
    æĪªåĽ¾
    -0.26
     collect
    -0.26
    POSITIVE LOGITS
    ipur
    0.29
    :///
    0.28
    _NE
    0.26
    _guide
    0.26
     erklärt
    0.25
     explaining
    0.25
    atal
    0.24
    ensure
    0.24
    atility
    0.23
    æ·±åħ¥äºĨ解
    0.23
    Activations Density 0.003%

    No Known Activations