© 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. 21728
    Prev
    Next
    INDEX
    Explanations

    mental health and cognition

    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
    å¿ĥåĬ¨
    -0.10
    人æ°Ķ
    -0.09
    èĭ´
    -0.08
    å¿ĥèĦı
    -0.08
    çĶŁåij½
    -0.08
    çļĦèĦļæŃ¥
    -0.08
     кÑĢови
    -0.08
    eworld
    -0.08
    箦
    -0.08
    NET
    -0.08
    POSITIVE LOGITS
    mente
    0.10
    ually
    0.10
    ifest
    0.09
    å³Ĵ
    0.09
    fully
    0.09
    idades
    0.09
    LOY
    0.08
    istic
    0.08
    ities
    0.08
    ogy
    0.08
    Activations Density 0.019%

    No Known Activations