© 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. 6773
    Prev
    Next
    INDEX
    Explanations

    Assigning blame/responsibility

    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
    æľĪä¸ĭ
    -0.25
    rompt
    -0.24
    atas
    -0.24
    紧缺
    -0.24
     Heater
    -0.24
    æīįçŁ¥éģĵ
    -0.23
    让ä»ĸ
    -0.23
     puis
    -0.23
    .Locale
    -0.23
     Phot
    -0.23
    POSITIVE LOGITS
    åı¯èĥ½æĢ§
    0.28
    htar
    0.28
    è§Ĩ为
    0.27
    æ¯Ķ
    0.27
    æĪIJ份
    0.26
    ered
    0.26
    essim
    0.26
    afe
    0.26
     recognise
    0.25
    åĪĨ为
    0.25
    Activations Density 0.139%

    No Known Activations