© 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. 60796
    Prev
    Next
    INDEX
    Explanations

    see TV

    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
     disb
    -0.09
    å¨ģåĬĽ
    -0.08
    unami
    -0.08
    çĽĪ
    -0.08
    éħį
    -0.08
     Desk
    -0.08
    è°µ
    -0.08
    åįģä½³
    -0.08
    xad
    -0.08
    伤å¿ĥ
    -0.08
    POSITIVE LOGITS
    修为
    0.09
    åį¦
    0.09
     Furious
    0.08
    ,,,
    0.08
    elf
    0.08
    éŀį
    0.08
    Ùĥس
    0.08
    åħħ满
    0.08
    è¯ī
    0.08
    æīĵåĵį
    0.08
    Activations Density 0.004%

    No Known Activations