© 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. 59052
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    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
    æĥ®
    -0.09
    èįĶæŀĿ
    -0.09
    åIJĮä¸ļ
    -0.08
    赦
    -0.08
    çĽij管éĥ¨éŨ
    -0.08
    é«ĺéĢŁ
    -0.08
    èĽĢ
    -0.08
    èīºæľ¯
    -0.08
    ä¸ŃåĽ½çī¹èī²
    -0.08
    éĹ®è¯¢
    -0.08
    POSITIVE LOGITS
    å·½
    0.10
    ä¿Ł
    0.10
     Rou
    0.10
    nels
    0.09
     Weinstein
    0.09
    AccessType
    0.08
    仪
    0.08
    带åĬ¨
    0.08
    ç¢İ
    0.08
    æŃ£å¤Ħäºİ
    0.08
    Activations Density 0.003%

    No Known Activations