© 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. 61933
    Prev
    Next
    INDEX
    Explanations

    thanks, congratulations, support, excited

    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
    ä¸įåľ¨ä¹İ
    -0.09
    è¦ģ害
    -0.09
    对èĩªå·±çļĦ
    -0.09
    pare
    -0.08
    èµİ
    -0.08
    è¦ģç´§
    -0.08
     Rag
    -0.08
    èµ°åĩº
    -0.08
    ä¸įçĪ±
    -0.08
    ç®į
    -0.08
    POSITIVE LOGITS
    nette
    0.11
    otime
    0.10
    èģĶç³»æĸ¹å¼ı
    0.09
     Gonzalez
    0.08
    åĸ·
    0.08
    ä¸ŃæľŁ
    0.08
    åħ±çĶŁ
    0.08
     далÑĮн
    0.08
    ettes
    0.08
     GPL
    0.08
    Activations Density 0.028%

    No Known Activations