© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39695
    Prev
    Next
    INDEX
    Explanations

    class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Northern
    -0.10
    orer
    -0.09
    antino
    -0.09
    ìĺ¹
    -0.09
    éĿĴæĺ¥
    -0.09
    åĩ¤åĩ°
    -0.09
    æ±ŁåįĹ
    -0.08
    oref
    -0.08
    ä¿¡ä»°
    -0.08
    éĺ²
    -0.08
    POSITIVE LOGITS
    rooms
    0.10
    (classes
    0.10
    .forName
    0.10
    room
    0.10
    :class
    0.10
    /classes
    0.09
    ç¹¼
    0.09
    .getClassName
    0.09
    .Classes
    0.09
    åĪĨãģij
    0.09
    Activations Density 0.162%

    No Known Activations