© 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. 3445
    Prev
    Next
    INDEX
    Explanations

    Chelmsford prison

    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
     cones
    -0.09
    çĸĥ
    -0.09
    IBUT
    -0.08
    墩
    -0.08
     Madden
    -0.08
    ób
    -0.08
    ounsel
    -0.08
    çıī
    -0.08
     lider
    -0.08
    èĭ¦
    -0.08
    POSITIVE LOGITS
    éĵ®
    0.10
    è¿Ļ两ç§į
    0.10
    æĢĿãģ£ãģŁ
    0.09
    é«ĺé¢Ŀ
    0.09
    å¥¥åľ°åĪ©
    0.09
    缸å½ĵ
    0.09
    ihn
    0.09
    ä¼ļéķ¿
    0.09
    cio
    0.09
    æ¶ĵ
    0.09
    Activations Density 0.012%

    No Known Activations