© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130678
    Prev
    Next
    INDEX
    Explanations

    percentages and rates

    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
     toe
    -0.33
    (cols
    -0.27
     staples
    -0.26
     betr
    -0.25
     Era
    -0.25
     inve
    -0.25
    éŨ
    -0.24
     collar
    -0.24
    æĹ¥æĬ¥ç¤¾
    -0.24
    ormal
    -0.23
    POSITIVE LOGITS
    edList
    0.28
     WARRANT
    0.27
    —they
    0.26
     INCLUDE
    0.26
     MODULE
    0.25
    —but
    0.25
     incumbent
    0.25
    anje
    0.25
     vag
    0.25
    rita
    0.24
    Activations Density 3.257%

    No Known Activations