© 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. 21033
    Prev
    Next
    INDEX
    Explanations

    licensed to

    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
    æī©
    -0.09
    æµģæ°´
    -0.08
    uden
    -0.08
    æĥ³å¿µ
    -0.08
    ibus
    -0.08
    çĮ·
    -0.07
     coz
    -0.07
     dub
    -0.07
    UCE
    -0.07
    s
    -0.07
    POSITIVE LOGITS
    èĢģ大
    0.10
    bie
    0.09
    鸷
    0.09
     конеÑĩно
    0.09
    åĿļå®ļä¸į移
    0.09
    ataire
    0.09
    .Undef
    0.09
    åĮį
    0.09
    irim
    0.08
    ä¸įçĶ¨æĭħå¿ĥ
    0.08
    Activations Density 0.113%

    No Known Activations