© 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. 48713
    Prev
    Next
    INDEX
    Explanations

    malignant diseases and cancer

    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
    çĻ¸
    -0.08
    ITAL
    -0.08
     McD
    -0.08
     Paramount
    -0.08
    Attrib
    -0.08
    thal
    -0.08
    æĹ¶æ®µ
    -0.08
    èµ·æĿ¥
    -0.07
    _attrib
    -0.07
     Chall
    -0.07
    POSITIVE LOGITS
    ivet
    0.09
    ernaut
    0.09
    usher
    0.08
    èģĶåIJĪä¼ļ
    0.08
    åºĨ幸
    0.08
    mere
    0.08
    agt
    0.08
    CEPT
    0.08
    erus
    0.08
    åħļåĨħ
    0.08
    Activations Density 0.301%

    No Known Activations