© 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. 18860
    Prev
    Next
    INDEX
    Explanations

    broke out, bag, nest, mental, went insane, hit, falling, up/down, chaos

    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
    ç»ıåİĨ
    -0.10
    毫ä¸į
    -0.09
    기ëıĦ
    -0.09
     effortless
    -0.09
    å·´
    -0.09
    eri
    -0.08
     âĻ
    -0.08
     cáºŃp
    -0.08
    çĨ¨
    -0.08
    å·´å·´
    -0.08
    POSITIVE LOGITS
    æįħ
    0.11
    éĻ·åħ¥äºĨ
    0.10
    çĪĨåıij
    0.09
    æİ©
    0.09
    å¼Ģå§ĭäºĨ
    0.09
    æ··æ·Ĩ
    0.09
    帷
    0.09
    æ··ä¹±
    0.09
     chaos
    0.08
    æģ£
    0.08
    Activations Density 0.171%

    No Known Activations