© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7085
    Prev
    Next
    INDEX
    Explanations

    Mixed context documents

    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
     gamm
    -0.27
     oft
    -0.25
    èĭ¦èĭ¦
    -0.24
    æĪª
    -0.24
    éĩİ
    -0.24
    (coll
    -0.24
     domain
    -0.23
    æ²īéĩį
    -0.23
    æĹłæ¯Ķ
    -0.23
    uya
    -0.23
    POSITIVE LOGITS
    åĴĮ个人
    0.29
    çijŁ
    0.27
    osen
    0.26
     such
    0.26
     duyá»ĩt
    0.26
    неÑģен
    0.26
    snow
    0.25
    ç¡®å®ļ
    0.25
    è¿Ļæł·çļĦè¯Ŀ
    0.25
    éĽª
    0.25
    Activations Density 0.044%

    No Known Activations