© 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. 9010
    Prev
    Next
    INDEX
    Explanations

    start or end of sentence

    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
    éķ¿æķĪ
    -0.27
    æĹ©
    -0.26
    gef
    -0.26
    erved
    -0.25
     '~/
    -0.25
     early
    -0.25
    freeze
    -0.25
    ãģĭãģ¤
    -0.25
    ilet
    -0.24
     flo
    -0.24
    POSITIVE LOGITS
    uzzi
    0.29
    té
    0.27
    ogne
    0.26
    纵
    0.25
    rowsers
    0.25
    檬
    0.24
    éĤ£ç§į
    0.24
     Rae
    0.24
    enan
    0.23
    å¿ĥä¸ŃçļĦ
    0.23
    Activations Density 0.786%

    No Known Activations