© 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. 40389
    Prev
    Next
    INDEX
    Explanations

    easy way

    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
    pone
    -0.10
    ally
    -0.10
    累累
    -0.10
    nal
    -0.10
    ned
    -0.10
    ä¸Ģä½ĵ
    -0.09
    亲çĪ±
    -0.09
    åŁ´
    -0.09
    åĬĽæ±Ĥ
    -0.09
    Äį
    -0.09
    POSITIVE LOGITS
     dÃłng
    0.21
    -minded
    0.13
    going
    0.11
     minded
    0.11
    äºĽ
    0.11
     جدا
    0.11
    rum
    0.11
    è¨ĢãģĪãģ°
    0.11
     enough
    0.10
    éĻ²
    0.10
    Activations Density 0.034%

    No Known Activations