© 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. 19298
    Prev
    Next
    INDEX
    Explanations

    don't know

    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
    çIJĨçĶ±
    -0.10
    ORM
    -0.09
     Brush
    -0.09
    hel
    -0.08
    ä»ĩ
    -0.08
     furn
    -0.08
    为é¦ĸ
    -0.08
    åĻľ
    -0.08
    çIJĨ工大åѦ
    -0.08
    aus
    -0.08
    POSITIVE LOGITS
    太é«ĺ
    0.10
     íĮIJ
    0.09
    lien
    0.09
    è°ģçŁ¥éģĵ
    0.09
    íĮIJ
    0.09
    åŁºåĩĨ
    0.09
    åįŀ
    0.08
    enses
    0.08
    illin
    0.08
    辨åĪ«
    0.08
    Activations Density 0.040%

    No Known Activations