© 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. 8321
    Prev
    Next
    INDEX
    Explanations

    Titles, roles, and computer terms

    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
    åijĹ
    -0.28
    èĥĮæĻ¯
    -0.26
    èĬĤèĥ½åĩıæİĴ
    -0.25
    illions
    -0.25
    åIJ§
    -0.24
    ensburg
    -0.24
    acie
    -0.24
    æ¹ĵ
    -0.24
    OMB
    -0.24
    æīĵåĩº
    -0.24
    POSITIVE LOGITS
    ç¨Ķ
    0.29
    ä¸ªé¡¹çĽ®
    0.29
    criptors
    0.24
     Absolute
    0.24
    visor
    0.24
    溱
    0.24
    _PF
    0.24
     Concert
    0.23
    vari
    0.23
     Young
    0.23
    Activations Density 0.007%

    No Known Activations