© 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. 48478
    Prev
    Next
    INDEX
    Explanations

    autism spectrum disorders and related language

    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
    é£ĺ
    -0.10
     Magnum
    -0.09
    ĤŃ
    -0.09
    å·¥å§Ķ
    -0.09
    Ặ
    -0.09
    lege
    -0.08
    大家åĪĨ享
    -0.08
    cce
    -0.08
     Porn
    -0.08
    orrh
    -0.08
    POSITIVE LOGITS
    çĶµåŃIJ产åĵģ
    0.10
     autism
    0.10
     autistic
    0.10
    åķ¸
    0.10
    alsy
    0.09
    วà¸Ķ
    0.09
     Autism
    0.09
    åѦåīį
    0.09
    -parent
    0.09
    天使
    0.09
    Activations Density 0.139%

    No Known Activations