© 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. 9153
    Prev
    Next
    INDEX
    Explanations

    technical 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
    weet
    -0.27
     Center
    -0.26
    声
    -0.25
    æĶ¶æĭ¾
    -0.24
    itches
    -0.24
    ucus
    -0.24
    PK
    -0.24
    ek
    -0.24
    èįĶæŀĿ
    -0.24
    æıIJ示
    -0.24
    POSITIVE LOGITS
    ote
    0.29
     :↵↵↵↵
    0.29
    åı¦ä¸Ģç§į
    0.28
    otent
    0.27
    oten
    0.26
    è´¹çİĩ
    0.26
    æŶéĹ´åĴĮ
    0.25
     \↵↵
    0.25
    åī§
    0.24
    Uvs
    0.24
    Activations Density 0.037%

    No Known Activations