© 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. 9046
    Prev
    Next
    INDEX
    Explanations

    hr

    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
     early
    -0.25
    åĪ©
    -0.25
     updating
    -0.25
    обÑĢаз
    -0.24
    æĹ©
    -0.24
    éĩĩ
    -0.24
    hpp
    -0.24
    è¡°èĢģ
    -0.24
     tar
    -0.23
     Fluid
    -0.23
    POSITIVE LOGITS
    getOption
    0.32
    ç»Ŀ大éĥ¨åĪĨ
    0.27
     Medal
    0.26
    developer
    0.26
    è¿ĻçĤ¹
    0.25
    åħ¨æĻ¯
    0.25
    atel
    0.24
    çļĦä¸ĢéĿ¢
    0.24
    çļĦ梦æĥ³
    0.24
    ilion
    0.24
    Activations Density 0.131%

    No Known Activations