© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    ranking or 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
    бо
    -0.09
    ç´į
    -0.08
    ç²¾åįİ
    -0.08
    ollo
    -0.08
    umm
    -0.08
    åIJĮç±»
    -0.07
    åħ¶æīĢ
    -0.07
    å¤ļæł·æĢ§
    -0.07
    éĺĶ
    -0.07
    çłį
    -0.07
    POSITIVE LOGITS
    thon
    0.10
    ä¸İæŶ
    0.10
    FormatException
    0.10
    MAND
    0.09
    èĢĮæĺ¯
    0.09
    Õ¹
    0.09
    ä¸Ģåı·
    0.09
    pora
    0.09
    ÑĩÑĥв
    0.09
    zte
    0.09
    Activations Density 0.040%

    No Known Activations