© 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. 39600
    Prev
    Next
    INDEX
    Explanations

    transportation or vehicles

    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
    诨
    -0.09
    åIJĪ约
    -0.09
    åı°ä¸Ĭ
    -0.09
    æĶ¶åĪ°äºĨ
    -0.09
     Consortium
    -0.08
    浴室
    -0.08
    æĻ¦
    -0.08
    æħ°éĹ®
    -0.08
    urry
    -0.08
    ional
    -0.08
    POSITIVE LOGITS
    æŃ¥è¡Į
    0.14
    åĩºè¡Į
    0.14
    è´Ń车
    0.13
    åħ¬åħ±äº¤éĢļ
    0.12
     mobility
    0.12
    交éĢļå·¥åħ·
    0.12
     car
    0.11
    è´Ńç½®
    0.11
     transportation
    0.11
     Mobility
    0.11
    Activations Density 0.075%

    No Known Activations