© 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. 38638
    Prev
    Next
    INDEX
    Explanations

    part number

    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
    åħľ
    -0.08
    缸
    -0.08
    è¡£
    -0.08
    éĻ¤å¤ĸ
    -0.08
    çij¶
    -0.07
     ho
    -0.07
    çļĦåij³éģĵ
    -0.07
    eut
    -0.07
     max
    -0.07
    åı£è¢ĭ
    -0.07
    POSITIVE LOGITS
    iggins
    0.10
    è·¡
    0.10
    -arrow
    0.09
    é©¿
    0.09
    æĭĽ
    0.09
    udas
    0.09
    adiens
    0.09
    å¤ļåľ°
    0.09
    æłİ
    0.09
    ä»ĸèĩªå·±
    0.09
    Activations Density 0.106%

    No Known Activations