© 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. 62376
    Prev
    Next
    INDEX
    Explanations

    projects and events

    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
    aka
    -0.10
    ç»Łæ²»
    -0.09
    æİī
    -0.08
    åĩłçĤ¹
    -0.08
    人æīį
    -0.08
    å¿Į
    -0.08
    ä¸įç®Ĺ
    -0.08
     пÑĢоÑģ
    -0.08
    sl
    -0.08
    aly
    -0.07
    POSITIVE LOGITS
    å½ĵåľ°çļĦ
    0.10
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.09
    å½ĵåľ°
    0.09
     bé
    0.09
    举æݪ
    0.09
    ://{
    0.09
    /ay
    0.09
    çĭ¬åħ·
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    çĶŁæľº
    0.09
    Activations Density 0.064%

    No Known Activations