© 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. 23378
    Prev
    Next
    INDEX
    Explanations

    scientific/technical jargon

    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
    ynchronously
    -0.31
    éĵħ
    -0.27
     unsub
    -0.27
    Performed
    -0.26
    ismet
    -0.26
    ivos
    -0.26
    ToFit
    -0.25
    éĿŀ常æĺİæĺ¾
    -0.25
    udeau
    -0.24
    illé
    -0.24
    POSITIVE LOGITS
     reform
    0.27
    éĤ£æ®µ
    0.25
    rl
    0.25
     rollback
    0.25
     Fac
    0.24
    press
    0.23
    ع
    0.23
    è¹´
    0.23
     collapse
    0.23
     Bayer
    0.23
    Activations Density 0.003%

    No Known Activations