© 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. 24766
    Prev
    Next
    INDEX
    Explanations

    Developed/invented

    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
    (tol
    -0.24
     wireType
    -0.24
    clearfix
    -0.23
    ìĸ´ìĦľ
    -0.23
     TIMEOUT
    -0.23
    boats
    -0.23
     microtime
    -0.23
    _ascii
    -0.23
    ports
    -0.23
    æĿĻ
    -0.23
    POSITIVE LOGITS
     Linked
    0.29
    çłĶ究人åijĺ
    0.26
    Orig
    0.26
    ongoose
    0.26
     cú
    0.25
    产åĵģçłĶåıij
    0.25
    æįIJèµł
    0.25
    ince
    0.25
    æ»ļåĬ¨
    0.25
     prof
    0.24
    Activations Density 0.012%

    No Known Activations