© 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. 57594
    Prev
    Next
    INDEX
    Explanations

    accessibility and disability

    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
    åĭIJ
    -0.09
    åī¥ç¦»
    -0.09
    çĦ¦çĤ¹
    -0.09
    妾
    -0.08
    迳
    -0.08
    åī¥å¤º
    -0.08
    неÑĢ
    -0.08
    ä¸įå¤Ł
    -0.08
    çĮľ
    -0.08
    å¸®ä½ł
    -0.08
    POSITIVE LOGITS
    å¾Ģè¿Ķ
    0.10
    骨
    0.10
     accessibility
    0.10
     handic
    0.09
    æĹħéĢĶ
    0.09
    çĹķ
    0.09
    æ®ĭçĸ¾
    0.09
    inson
    0.09
    容
    0.09
    _accessible
    0.09
    Activations Density 0.035%

    No Known Activations