© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    look no further than

    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
    åĤį
    -0.09
    æ²ī
    -0.09
    .Builder
    -0.09
    èĤĵ
    -0.08
    ä¸įå¤Ł
    -0.08
    ä¸įç»ı
    -0.08
    åľ¨ç¾İåĽ½
    -0.08
    å¦Ĥæŀľä¸į
    -0.08
    åĪģ
    -0.08
     toler
    -0.08
    POSITIVE LOGITS
     Amar
    0.10
    è¿Ļ家
    0.10
    çĹĽçĤ¹
    0.09
    igate
    0.09
    èĢĮåİ»
    0.09
    å°±æĥ³
    0.09
    åĪ°ä½į
    0.08
    伸åĩº
    0.08
    为æ°ij
    0.08
    wind
    0.08
    Activations Density 0.006%

    No Known Activations