© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17520
    Prev
    Next
    INDEX
    Explanations

    new, advice, questions, plea, decision

    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
    åħ¶
    -0.11
     suo
    -0.10
     seu
    -0.10
    对èĩªå·±çļĦ
    -0.09
    ä»ĸå¦Ī
    -0.09
    她çļĦ
    -0.09
    ä½łçļĦ
    -0.08
    串
    -0.08
    onen
    -0.08
     banging
    -0.08
    POSITIVE LOGITS
     own
    0.11
     OWN
    0.11
     Own
    0.10
    Own
    0.10
    à¹Ģà¸Ńà¸ĩ
    0.10
     depreci
    0.09
    缸åºĶ
    0.09
    OWN
    0.09
    åľ¨äº¬
    0.09
     اÙĦجÙħÙĩ
    0.09
    Activations Density 0.153%

    No Known Activations