© 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. 8081
    Prev
    Next
    INDEX
    Explanations

    go run

    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
    éĤĢ
    -0.10
    .isNull
    -0.09
    ä¸ĭéĿ¢å°±
    -0.08
    满
    -0.08
    ТÐķ
    -0.08
    å·¡åĽŀ
    -0.08
    åıijæĺİä¸ĵåĪ©
    -0.08
    夫
    -0.08
    åĵĪåĵĪ
    -0.08
    åĮĹæĸ¹
    -0.08
    POSITIVE LOGITS
    èľļ
    0.11
    亲åıĭ
    0.10
    ä¸ĢåŃĹ
    0.10
     оÑĤз
    0.10
    æ¿ī
    0.10
    åĶģ
    0.10
    修为
    0.09
    åľ¨ç½ij绾ä¸Ĭ
    0.09
     оÑĤзÑĭв
    0.09
    æľįåĬ¡åĮº
    0.09
    Activations Density 0.002%

    No Known Activations