© 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. 19827
    Prev
    Next
    INDEX
    Explanations

    urinalysis medical tests

    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
     Pou
    -0.09
     Goat
    -0.09
    éĤ£
    -0.09
    orest
    -0.09
    Spinner
    -0.08
    èŁĴ
    -0.08
    ç¿ģ
    -0.08
    mium
    -0.08
    å¤ļå±Ĥ次
    -0.08
     Recovery
    -0.08
    POSITIVE LOGITS
    亲人
    0.13
    æ¼Ĥæµģ
    0.10
    åĵķ
    0.10
    feld
    0.09
    çĶ¸
    0.09
    è¿ģ移
    0.09
    .constructor
    0.09
     Eff
    0.09
     Wick
    0.09
    åĮ¿åIJį
    0.08
    Activations Density 0.354%

    No Known Activations