© 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. 8681
    Prev
    Next
    INDEX
    Explanations

    odont

    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
     $č↵
    -0.29
    æ±
    -0.28
    %č↵
    -0.26
    \č↵
    -0.26
    ()č↵
    -0.25
     ",č↵
    -0.25
    (){č↵
    -0.25
    lemen
    -0.24
     anytime
    -0.23
    ()</
    -0.23
    POSITIVE LOGITS
    å¢ĥ
    0.28
    æĺ¯åı¯ä»¥
    0.25
    asse
    0.25
    -linked
    0.25
    asha
    0.25
    伺
    0.24
     mistress
    0.23
    vention
    0.23
    æĺ¯æĪij
    0.23
    åı°ä¸Ĭ
    0.23
    Activations Density 0.017%

    No Known Activations