© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9323
    Prev
    Next
    INDEX
    Explanations

    accuracy or errors

    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
    _allocated
    -0.09
    alar
    -0.09
    段
    -0.09
    PROTO
    -0.09
    ersions
    -0.08
    éģĩè§ģ
    -0.08
    ivos
    -0.08
    åı¯è§Ĥ
    -0.08
     Barker
    -0.08
     PPC
    -0.08
    POSITIVE LOGITS
    趺
    0.10
    èĬľ
    0.10
    æĺİæĹ¥
    0.09
    æıIJä¾ĽæĽ´å¤ļ
    0.09
    ä¸įä¿¡
    0.09
    лиз
    0.09
    忽
    0.09
    æ³»
    0.09
    å¸ľ
    0.08
    èı©
    0.08
    Activations Density 0.014%

    No Known Activations