© 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. 37864
    Prev
    Next
    INDEX
    Explanations

    subsequently, subconscious, sub-menu, substantial, substations, submit, subordinate

    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
    ä½Ĩ对äºİ
    -0.10
    ëĦĪ
    -0.09
    æŬ
    -0.08
    çķİ
    -0.08
     Bronze
    -0.08
    åĵ®
    -0.08
    olina
    -0.08
    ILT
    -0.08
     Benton
    -0.08
     Fior
    -0.08
    POSITIVE LOGITS
    (sub
    0.10
    -sub
    0.09
    æį¢åı¥è¯Ŀ
    0.09
    å¾®å¦Ļ
    0.09
    飬
    0.08
    çĥ
    0.08
    æ¯ķä¸ļåIJİ
    0.08
    OC
    0.08
    =sub
    0.08
     SUP
    0.08
    Activations Density 0.022%

    No Known Activations