© 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. 20-TRANSCODER-HP
    7. 62876
    Prev
    Next
    INDEX
    Explanations

    technical documentation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odelist
    -0.26
    èķī
    -0.25
    @Injectable
    -0.24
    æłĵ
    -0.23
     Injectable
    -0.23
    Girls
    -0.23
    issional
    -0.22
     Fou
    -0.22
    交ç»Ļ
    -0.22
    ARS
    -0.22
    POSITIVE LOGITS
    åı¸
    0.29
    对äºİ
    0.25
    ZE
    0.24
    éĶ¥
    0.24
    ecute
    0.24
     fell
    0.24
    enez
    0.24
    åŁºæľ¬ä¿¡æģ¯
    0.23
     dens
    0.23
    fell
    0.23
    Activations Density 30.092%

    No Known Activations