© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    drug efficacy and resistance

    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
    åģ¥åº·ç®¡çIJĨ
    -0.10
    çĵ¯
    -0.09
    é©·
    -0.09
    OUCH
    -0.09
    åľ³
    -0.09
    ä¸įåΰä½į
    -0.09
    uren
    -0.09
    èµī
    -0.09
    egas
    -0.09
    ç¬
    -0.09
    POSITIVE LOGITS
    æķijåĬ©
    0.10
    abb
    0.09
    ABB
    0.09
     drug
    0.08
    Drug
    0.08
    åĤ¨å¤ĩ
    0.08
    æķijæ²»
    0.08
    çĻ½éĽª
    0.08
    æªĢ
    0.08
    æķij
    0.08
    Activations Density 0.493%

    No Known Activations