© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    seeds and fruit dispersal

    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
    磮
    -0.10
    ç²¾å¿ĥ
    -0.10
    иÑĪ
    -0.10
    å¢Ĵ
    -0.09
    æĶ¾æīĭ
    -0.09
    妥åĸĦ
    -0.09
    å¤ĸçķĮ
    -0.09
    ç´łè´¨æķĻèĤ²
    -0.09
     subj
    -0.09
    èµ°
    -0.09
    POSITIVE LOGITS
    çĬ¹
    0.10
    æ¯ķä¸ļåIJİ
    0.09
    ä¼¼
    0.09
    çĮ¶
    0.09
    æµģæ·Į
    0.09
    åIJ¸å¼ķ
    0.08
    çĵľ
    0.08
    fen
    0.08
     Ou
    0.08
    _METHOD
    0.08
    Activations Density 0.028%

    No Known Activations