© 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. 12-TRANSCODER-HP
    7. 23269
    Prev
    Next
    INDEX
    Explanations

    photography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    丰å¯ĮçļĦ
    -0.27
    omain
    -0.27
    è¯Ŀ说
    -0.26
    __*/
    -0.26
     NPR
    -0.26
    krä
    -0.26
    powered
    -0.26
    olars
    -0.25
     Cascade
    -0.25
    çĤ¹æ»´
    -0.25
    POSITIVE LOGITS
    allel
    0.28
     cure
    0.27
    éģį
    0.26
    uum
    0.25
     cel
    0.25
     ITEM
    0.25
    items
    0.24
    æĬ½åĩº
    0.24
     Item
    0.24
     ob
    0.24
    Activations Density 0.008%

    No Known Activations