© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    ordering of elements

    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
    /remove
    -0.11
    çĿĢæīĭ
    -0.10
    æĴĴ
    -0.10
    à¸ķล
    -0.10
    ãĤįãģĨ
    -0.10
    sWith
    -0.09
    nel
    -0.09
    ings
    -0.09
    ãģ¾ãģ¾
    -0.09
    soc
    -0.09
    POSITIVE LOGITS
    ly
    0.11
    redients
    0.11
     done
    0.10
    done
    0.10
    _done
    0.10
    ÑĤон
    0.10
    redient
    0.10
    hausen
    0.09
    ÑģÑı
    0.09
     Ceremony
    0.09
    Activations Density 0.299%

    No Known Activations