© 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. 9294
    Prev
    Next
    INDEX
    Explanations

    plenty

    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
    (es
    -0.23
    ây
    -0.22
    ilogy
    -0.21
    鼬
    -0.21
    æĢ§å¼º
    -0.21
    跨度
    -0.21
    å¤įæĿĤçļĦ
    -0.21
    èĪĤ
    -0.21
    periences
    -0.20
    å¿ħãģļ
    -0.20
    POSITIVE LOGITS
    omat
    0.29
    erator
    0.27
    ä¸İåIJ¦
    0.27
    _PM
    0.26
    omp
    0.25
    sofar
    0.25
     compl
    0.24
    l
    0.24
    egie
    0.24
     grips
    0.24
    Activations Density 2.339%

    No Known Activations