© 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. 51158
    Prev
    Next
    INDEX
    Explanations

    note or book

    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
    opus
    -0.09
    itori
    -0.08
    rade
    -0.08
    èĺħ
    -0.08
    äºĶéĩij
    -0.08
    ä¸Ģæľ¬
    -0.08
    CESS
    -0.08
    ptime
    -0.08
     Lad
    -0.08
     delt
    -0.08
    POSITIVE LOGITS
    çݯèĬĤ
    0.10
    isko
    0.09
    eon
    0.09
    isse
    0.09
    enstein
    0.09
    feb
    0.09
    باط
    0.08
    äºĶä¸Ģ
    0.08
    ç¤ģ
    0.08
    ä¸ĭåįĬ
    0.08
    Activations Density 0.064%

    No Known Activations