© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51007
    Prev
    Next
    INDEX
    Explanations

    ciprofloxacin

    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
     Bor
    -0.09
    ingham
    -0.09
    ham
    -0.09
     Dana
    -0.09
    bor
    -0.09
    ç²¾éĢļ
    -0.09
     Gore
    -0.09
     Draft
    -0.08
    è¿ĽåĮĸ
    -0.08
     borr
    -0.08
    POSITIVE LOGITS
    åİŁæľī
    0.09
    æ¦ķ
    0.09
    亲èĩª
    0.09
    纡
    0.09
    ä¼łéĹ»
    0.08
    西å®ģ
    0.08
    ç¿Ĭ
    0.08
    жд
    0.08
    çĥĿ
    0.08
    èµŁ
    0.08
    Activations Density 0.005%

    No Known Activations