© 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. 17326
    Prev
    Next
    INDEX
    Explanations

    disability and related conditions

    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
     Seymour
    -0.09
    è¿ĩåħ³
    -0.08
    rant
    -0.08
    åĽŀé¦Ī
    -0.08
    èľ»
    -0.08
    å¿ĹæĦ¿èĢħ
    -0.08
    çĿĢçľ¼äºİ
    -0.08
    lake
    -0.08
    å¦Ĥä½ķçľĭå¾ħ
    -0.08
    解æĶ¾æĢĿæĥ³
    -0.08
    POSITIVE LOGITS
    åĭ¾
    0.11
    èĵĦ
    0.11
    æĬij
    0.10
    å·¨
    0.09
    çİīçŁ³
    0.09
    asurer
    0.09
    çİ°å®ŀä¸Ń
    0.09
    带åĪ°
    0.09
    .Metro
    0.09
    ç¿ħ
    0.09
    Activations Density 0.138%

    No Known Activations