© 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. 23168
    Prev
    Next
    INDEX
    Explanations

    Guessing and prediction

    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
    -sectional
    -0.30
     Govern
    -0.28
    apan
    -0.27
    个ä½ĵ
    -0.26
    /styles
    -0.26
    artner
    -0.26
    guess
    -0.25
    çĮľ
    -0.25
     guesses
    -0.25
     onward
    -0.24
    POSITIVE LOGITS
    æ¼ıæ´ŀ
    0.32
    vi
    0.30
    æĬ¥åijĬ
    0.30
     unf
    0.29
    obia
    0.28
    å®Ŀè´µçļĦ
    0.28
     report
    0.27
    лага
    0.27
     reports
    0.27
     grids
    0.26
    Activations Density 0.001%

    No Known Activations