© 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. 36541
    Prev
    Next
    INDEX
    Explanations

    because of that

    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
    icode
    -0.09
    oused
    -0.09
    ifton
    -0.09
    -INF
    -0.09
    ilig
    -0.09
    chied
    -0.09
    ilian
    -0.09
    å¾Īéĩįè¦ģçļĦ
    -0.09
    mag
    -0.09
    .addListener
    -0.09
    POSITIVE LOGITS
    ä¸Ģ代
    0.10
    é¢ĦåijĬ
    0.10
    éĢĦ
    0.09
    zza
    0.08
    è°Ľ
    0.08
    çļĦåıijçĶŁ
    0.08
    å¸Ĥåľºä¸»ä½ĵ
    0.08
    нÑıÑĤие
    0.08
    ä½İäºİ
    0.08
    ä¸įä¸ĭ
    0.08
    Activations Density 0.286%

    No Known Activations