© 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. 11560
    Prev
    Next
    INDEX
    Explanations

    drivers or driver

    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
    èıħ
    -0.10
    ense
    -0.10
    åĨĴ
    -0.09
    è¿IJåĬ¨ä¼ļ
    -0.09
    éĤ£æ®µ
    -0.09
    磻
    -0.08
    Ìģ
    -0.08
    ç®Ģ称
    -0.08
    æ¹İ
    -0.08
    icolon
    -0.08
    POSITIVE LOGITS
    ocy
    0.10
    åĮĹ京æŶéĹ´
    0.09
    ICI
    0.09
    tp
    0.09
    ени
    0.08
     Alic
    0.08
    зÑĭ
    0.08
    orum
    0.08
    åıŁ
    0.08
    spo
    0.08
    Activations Density 0.044%

    No Known Activations