© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7362
    Prev
    Next
    INDEX
    Explanations

    the following

    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
    imb
    -0.10
    ä¸Ĭè¿°
    -0.09
     previously
    -0.09
    çİ°æľīçļĦ
    -0.09
    è¿Ļç¯ĩ
    -0.08
    8
    -0.08
    常çĶ¨çļĦ
    -0.08
     Tow
    -0.08
    9
    -0.08
    è¿Ļ两个
    -0.08
    POSITIVE LOGITS
    éĩĮéĿ¢
    0.10
    å®ĥ
    0.10
    ç»ĵæŀľ
    0.10
    åIJİæŀľ
    0.10
    缺çĤ¹
    0.09
    èĬ¹
    0.09
    .dds
    0.09
     ëĤ´ìļ©
    0.09
    ç¬ŀ
    0.09
    GINE
    0.09
    Activations Density 0.279%

    No Known Activations