© 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. 8869
    Prev
    Next
    INDEX
    Explanations

    Medical problems

    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
    æĸ¯å¡Ķ
    -0.29
    inh
    -0.28
     translated
    -0.27
     Css
    -0.26
    é¢ļ
    -0.26
    ä½ľä¸ļ
    -0.25
    -as
    -0.24
    èħŃ
    -0.24
    /from
    -0.24
     bır
    -0.24
    POSITIVE LOGITS
    éłĪ
    0.28
    åĬłå¼ºå¯¹
    0.27
    é¡»
    0.25
    _needed
    0.25
    shr
    0.24
    imin
    0.24
    peats
    0.24
    datable
    0.24
    åıªå¥½
    0.24
    worthy
    0.24
    Activations Density 0.004%

    No Known Activations