© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22379
    Prev
    Next
    INDEX
    Explanations

    managed to VERB

    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
    ç®Ģ缴
    -0.11
    æģ¨ä¸įå¾Ĺ
    -0.11
    ç®Ģ缴æĺ¯
    -0.10
    æĢķ
    -0.10
    oin
    -0.10
    以便
    -0.10
    è°ģçŁ¥éģĵ
    -0.09
    åħ¬çĦ¶
    -0.09
    éļıåį³
    -0.09
     обÑıзаÑĤелÑĮно
    -0.09
    POSITIVE LOGITS
     somew
    0.10
    GetValue
    0.10
    ties
    0.08
     somehow
    0.08
    idades
    0.08
     loophole
    0.08
    lich
    0.08
     Juda
    0.08
    ird
    0.08
     sq
    0.08
    Activations Density 0.011%

    No Known Activations