© 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. 36467
    Prev
    Next
    INDEX
    Explanations

    must not, must have, must use

    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
    expert
    -0.09
    åĪĿ次
    -0.09
     Dun
    -0.09
    ombo
    -0.09
    æ¯į
    -0.09
     maybe
    -0.08
    iscard
    -0.08
    anus
    -0.08
    omat
    -0.08
    第ä¸Ģ次
    -0.08
    POSITIVE LOGITS
    ä¹Łåıªèĥ½
    0.14
    -have
    0.14
    è¦ģæľī
    0.13
    /w
    0.12
    ered
    0.12
    ache
    0.10
    çĦ¶æĺ¯
    0.10
     знаÑĤÑĮ
    0.10
    尽快
    0.10
    ioned
    0.10
    Activations Density 0.032%

    No Known Activations