© 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. 23971
    Prev
    Next
    INDEX
    Explanations

    somewhere

    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
    çģ«çĥ§
    -0.09
    åı¸æľº
    -0.08
    è·»
    -0.08
     Wo
    -0.08
    APS
    -0.08
    æ¯ıæ¯ı
    -0.08
    åIJģ
    -0.08
    liable
    -0.08
    æ¹ĺæ½Ń
    -0.08
     sometimes
    -0.08
    POSITIVE LOGITS
     somewhere
    0.17
    ä»Ģä¹Īåľ°æĸ¹
    0.16
    æŁIJ个
    0.14
    æŁIJ
    0.11
    æŁIJä¸Ģ
    0.11
    ewhere
    0.11
    è§ĴèIJ½
    0.10
    æ·±å¤Ħ
    0.09
     somew
    0.09
    管çIJĨä½ĵç³»
    0.09
    Activations Density 0.022%

    No Known Activations