© 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. 7948
    Prev
    Next
    INDEX
    Explanations

    Location/residence

    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
     AppComponent
    -0.27
    为èĩªå·±
    -0.26
    -ref
    -0.26
    OLON
    -0.26
    æ¯ıä¸Ģ次
    -0.25
    .Ref
    -0.25
    åıijçİ°èĩªå·±
    -0.25
    é¡¹çĽ®å»ºè®¾
    -0.24
    æ¯ıä¸Ģ个人
    -0.24
    pane
    -0.24
    POSITIVE LOGITS
    acle
    0.27
    łģ
    0.27
    æĸĮ
    0.26
    岸
    0.26
     Canyon
    0.25
    alis
    0.25
    itled
    0.25
    dbl
    0.25
    dat
    0.25
     dé
    0.25
    Activations Density 0.024%

    No Known Activations