© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37065
    Prev
    Next
    INDEX
    Explanations

    valid species classification

    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
    éĢ®
    -0.10
    åĬłå¿«å»ºè®¾
    -0.09
    IMIT
    -0.08
    åĤ¬
    -0.08
    ä¼ı
    -0.08
     Lev
    -0.08
    çĦ¦
    -0.08
    衲
    -0.08
    åĸ»
    -0.08
    çĪ¶åŃIJ
    -0.07
    POSITIVE LOGITS
    åĶ®åIJİ
    0.10
     Canter
    0.09
    zens
    0.09
    oming
    0.09
    åĪĨéħį
    0.09
    æĭ³å¤´
    0.09
    æłª
    0.08
    å¤ĸè§Ĥ
    0.08
    oise
    0.08
    åĵģç§į
    0.08
    Activations Density 0.397%

    No Known Activations