© 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. 108418
    Prev
    Next
    INDEX
    Explanations

    logs and 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
    æķijåij½
    -0.28
    vas
    -0.27
    [method
    -0.27
     Wig
    -0.26
    mö
    -0.26
    å°±èĥ½
    -0.25
    åĽ½åĬ¡
    -0.25
    -election
    -0.25
     davon
    -0.24
    @student
    -0.24
    POSITIVE LOGITS
    pack
    0.28
    è¿ŀ
    0.26
    åĨįçĶŁ
    0.24
    æĮģç»Ń
    0.24
     successful
    0.23
     mies
    0.23
    纪
    0.23
    æĻ®
    0.23
    å®īå®ģ
    0.23
    ActionResult
    0.23
    Activations Density 1.239%

    No Known Activations