© 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. 31312
    Prev
    Next
    INDEX
    Explanations

    problem or issue

    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
    ADS
    -0.09
    èĸ¨
    -0.09
    å¹ķ
    -0.09
    runner
    -0.09
    idel
    -0.09
    dle
    -0.09
     dese
    -0.08
    ales
    -0.08
    åĩĨ
    -0.08
    ads
    -0.08
    POSITIVE LOGITS
     problem
    0.23
    çļĦéĹ®é¢ĺ
    0.23
    problem
    0.20
     пÑĢоблем
    0.19
     Problem
    0.19
    éĹ®é¢ĺ
    0.18
    è¿Ļ个éĹ®é¢ĺ
    0.18
    Problem
    0.18
    åķıé¡Į
    0.17
    _problem
    0.17
    Activations Density 0.199%

    No Known Activations