© 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. 23-TRANSCODER-HP
    7. 23979
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TTY
    -0.25
    agrid
    -0.24
     rode
    -0.24
    éł»éģĵ
    -0.23
    creen
    -0.23
     parcels
    -0.23
    æĻ®æŁ¥
    -0.23
     recorded
    -0.23
    agra
    -0.23
     endanger
    -0.23
    POSITIVE LOGITS
     Intr
    0.30
     commenter
    0.28
     Princip
    0.26
    åĴª
    0.25
     Import
    0.24
    æĸ°ä¸Ģ代
    0.24
    æIJĶ
    0.23
    æĬ±
    0.23
    :Set
    0.23
    iffer
    0.23
    Activations Density 0.008%

    No Known Activations