© 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. 19-TRANSCODER-HP
    7. 8293
    Prev
    Next
    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ°
    -0.27
    çĩķ
    -0.27
    çī¹æ®Ĭ
    -0.26
    éĩİ
    -0.25
    满
    -0.25
     Legend
    -0.25
     overcrow
    -0.24
    æľīä¸Ģä½į
    -0.24
    usta
    -0.24
    æľīä¸Ģ
    -0.24
    POSITIVE LOGITS
    注è§Ĩ
    0.27
    æĮĿ
    0.27
    é¦Ļæ°´
    0.26
     :=↵
    0.26
    berg
    0.25
    udeau
    0.25
    鬯
    0.25
     guard
    0.24
     ÑĦиÑĢ
    0.24
     terme
    0.23
    Activations Density 0.003%

    No Known Activations