© 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. 64501
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions/scientific language

    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
    versions
    -0.28
    eld
    -0.27
    credited
    -0.26
    åĽŀèIJ½
    -0.26
    ceptors
    -0.26
    unami
    -0.26
    ervers
    -0.26
    Ļ¨
    -0.25
    reshold
    -0.25
    åĽł
    -0.25
    POSITIVE LOGITS
    读åIJİ
    0.30
    abbo
    0.27
     '../../../../../
    0.26
    ega
    0.26
    ventus
    0.24
     months
    0.24
    ød
    0.24
    娣
    0.23
    äºĨåIJĹ
    0.23
    å¾ħãģ¡
    0.23
    Activations Density 8.748%

    No Known Activations