© 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. 51851
    Prev
    Next
    INDEX
    Explanations

    world leader

    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
    ç²¾é«ĵ
    -0.09
    ime
    -0.08
    imes
    -0.08
    ạn
    -0.07
     Mons
    -0.07
    aga
    -0.07
     Rent
    -0.07
    licht
    -0.07
    çļĦå½±åĵį
    -0.07
    èĻ½è¯´
    -0.07
    POSITIVE LOGITS
    æĭĪ
    0.11
    æłĩæĺİ
    0.11
    æīĭæĦŁ
    0.10
    æħ·
    0.10
    械
    0.09
    виÑģ
    0.09
    å¿ĥéĩĮ
    0.09
    aybe
    0.09
    senal
    0.09
    åij³éģĵ
    0.09
    Activations Density 0.030%

    No Known Activations