© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20678
    Prev
    Next
    INDEX
    Explanations

    freezing temperatures and cold weather

    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
    è±ģ
    -0.10
    æķ¦
    -0.09
    ä¸ĬåįĬå¹´
    -0.09
    æļijæľŁ
    -0.09
     Ro
    -0.09
    æļij
    -0.09
    Summer
    -0.08
    éĻ·
    -0.08
    summer
    -0.08
    çĦ±
    -0.08
    POSITIVE LOGITS
    åĨ»ç»ĵ
    0.09
    éĻįåΰ
    0.09
    积æŀģæĢ§
    0.09
    çłŃ
    0.09
    éļ¾åıĹ
    0.09
    éĹ»
    0.08
    AGON
    0.08
    严éĩįå½±åĵį
    0.08
    建çŃij设计
    0.08
    åĨ·åĨ»
    0.08
    Activations Density 0.053%

    No Known Activations