© 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. 51354
    Prev
    Next
    INDEX
    Explanations

    negative sentiment / bad quality

    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
    èĻŀ
    -0.10
    icol
    -0.10
    ordinate
    -0.09
    åı¯æĥľ
    -0.09
     intimidate
    -0.09
    éĻį温
    -0.09
    _procs
    -0.09
    LOPT
    -0.09
    åIJijåīį
    -0.09
     interrogation
    -0.09
    POSITIVE LOGITS
    ç³Łç³ķ
    0.11
    ä¸įåłª
    0.10
    æĶ¾åĩº
    0.09
    æĥ¨
    0.09
    ä¹Łè¦ģ
    0.09
     poor
    0.08
    çīĩåŃIJ
    0.08
    蹩
    0.08
    ç¢ľ
    0.08
    æĶ¾å¼Ģ
    0.08
    Activations Density 0.045%

    No Known Activations