© 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. 22714
    Prev
    Next
    INDEX
    Explanations

    scientific/technical topics

    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
    天ä¸Ĭ
    -0.28
    é¹Ĺ
    -0.26
    éļĶçĿĢ
    -0.26
    太
    -0.26
    å¸Ŀ
    -0.25
     rail
    -0.25
    æ£ĢéªĮ
    -0.25
     restriction
    -0.25
     cele
    -0.25
    pherd
    -0.25
    POSITIVE LOGITS
    cir
    0.26
     categoryName
    0.26
    .tf
    0.25
    aviest
    0.25
    lots
    0.25
    tons
    0.25
    æı½
    0.25
    å¥
    0.24
    çİ·
    0.24
    çŃĴ
    0.24
    Activations Density 0.000%

    No Known Activations