© 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. 107270
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    bounce
    -0.27
    inka
    -0.26
     souls
    -0.26
     Thames
    -0.25
    TabPage
    -0.25
    bish
    -0.25
    èĢĨ
    -0.25
     ÑģобÑģÑĤвенно
    -0.25
     Bodies
    -0.25
    ldb
    -0.24
    POSITIVE LOGITS
    Sdk
    0.34
     pride
    0.28
     credit
    0.28
     operated
    0.27
    ipl
    0.27
    ä¿¡çĶ¨
    0.26
    Har
    0.26
     har
    0.26
     arg
    0.26
     vir
    0.25
    Activations Density 3.743%

    No Known Activations