© 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. 9104
    Prev
    Next
    INDEX
    Explanations

    last year

    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
    å½ĵæĹ¥
    -0.10
    åīįä¸Ģ天
    -0.10
    å½ĵ天
    -0.10
    æľ¬æ¬¡
    -0.09
    åĪ°æŶåĢĻ
    -0.09
     далÑĮÑĪе
    -0.09
    æ·±å¤Ħ
    -0.09
     lik
    -0.09
    æľ¬èº«çļĦ
    -0.08
    æĪijå½ĵæŶ
    -0.08
    POSITIVE LOGITS
    çĶŁæķĪ
    0.09
    éĢļè¡Į
    0.09
    با
    0.09
    /up
    0.09
    ëĭ¬
    0.08
    reur
    0.08
    å°±æľī
    0.08
    atal
    0.08
    aurant
    0.08
    ç¼ħ
    0.08
    Activations Density 0.037%

    No Known Activations