© 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. 31-TRANSCODER-HP
    7. 17741
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åįģ足
    -0.27
    .freeze
    -0.26
    arrant
    -0.26
     prive
    -0.25
    nev
    -0.25
    ABLE
    -0.25
     commentator
    -0.25
     бил
    -0.25
    atcher
    -0.25
     commentary
    -0.25
    POSITIVE LOGITS
    ä¹Ī
    0.30
    å¡«åħħ
    0.30
     Ã¶ÄŁren
    0.28
    享
    0.27
    æī§è¡Į
    0.26
    rcode
    0.26
    çģ«
    0.26
    UD
    0.25
    æį§
    0.24
    ä¹İ
    0.23
    Activations Density 0.103%

    No Known Activations