© 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. 8073
    Prev
    Next
    INDEX
    Explanations

    bring your own device

    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
    æī¹æ¬¡
    -0.09
    localized
    -0.09
    åŃĶéĽĢ
    -0.09
    iset
    -0.08
    缮çļĦåľ¨äºİ
    -0.08
     еÑīÑij
    -0.08
    åĨ¬åŃ£
    -0.08
    æĹħéĢĶ
    -0.08
    æıIJ款
    -0.08
    æľĪä¸Ń
    -0.08
    POSITIVE LOGITS
    èĩªå¸¦
    0.12
    çĶ¨èĩªå·±çļĦ
    0.12
    çİ°æľīçļĦ
    0.12
    åİŁæľīçļĦ
    0.12
    æľīèĩªå·±çļĦ
    0.10
    çĨŁæĤīçļĦ
    0.10
    å·²æľī
    0.10
     wÅĤas
    0.10
    èĩªæľī
    0.10
    ä¸įå¿į
    0.09
    Activations Density 0.116%

    No Known Activations