© 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. 4470
    Prev
    Next
    INDEX
    Explanations

    criticism of officials or policies

    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
    hem
    -0.11
    æĦīå¿«
    -0.11
    esto
    -0.11
    anger
    -0.10
    ãĢħ
    -0.10
    ickle
    -0.09
    åĿĢ
    -0.09
    thing
    -0.09
    teenth
    -0.09
    uilt
    -0.09
    POSITIVE LOGITS
     acclaim
    0.09
    éĿ¢å®¹
    0.09
     acclaimed
    0.08
    ical
    0.08
    飧
    0.08
    å·´å·´
    0.08
    çļĦçľ¼åħī
    0.08
    -minded
    0.08
    åĢĻ
    0.08
    åľ°æ®µ
    0.08
    Activations Density 0.022%

    No Known Activations