© 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. 48287
    Prev
    Next
    INDEX
    Explanations

    considering or given

    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
    æľīçĶ¨çļĦ
    -0.10
    å®ķ
    -0.09
    adol
    -0.09
    èĩĬ
    -0.09
    åĽ¢
    -0.08
    ãģķãĤī
    -0.08
    å®Ľå¦Ĥ
    -0.08
    æ¡Ģ
    -0.08
    ä¾
    -0.08
    like
    -0.08
    POSITIVE LOGITS
    è¿Ľåĩº
    0.09
     Hob
    0.08
     ÐłÐ°Ñģ
    0.08
    owo
    0.08
    æĪijå½ĵæŶ
    0.08
    Ñĩи
    0.08
    æĪij个人
    0.08
    ÑĤал
    0.08
    ç¥ŀç»ıç³»ç»Ł
    0.08
    WC
    0.08
    Activations Density 0.016%

    No Known Activations