© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16580
    Prev
    Next
    INDEX
    Explanations

    fall, falling, fallen

    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
    Negative Logits
    çĽ²çĽ®
    -0.08
    /native
    -0.08
    bate
    -0.08
    æ¯ĶåĪ©
    -0.08
    inery
    -0.08
    erate
    -0.08
    Ñģид
    -0.08
    æ¶Ī
    -0.08
    ropy
    -0.08
    ifice
    -0.08
    POSITIVE LOGITS
    å¥ł
    0.11
    Permanent
    0.11
    æĵĤ
    0.09
    ä»»æľŁ
    0.09
    åľŃ
    0.09
    æ°¸ä¹ħ
    0.09
    è¡į
    0.09
    éĻĽ
    0.09
    èIJ½åľ¨
    0.09
     Ñģеб
    0.09
    Activations Density 0.023%

    No Known Activations