© 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. 33949
    Prev
    Next
    INDEX
    Explanations

    change, shift, reversal, reconsider

    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
    æĥ³åĥı
    -0.09
    legalArgumentException
    -0.09
    _mapping
    -0.09
    çŃīçī¹çĤ¹
    -0.08
    ä¸ĵ享
    -0.08
    èĨĤ
    -0.08
    家ä½ı
    -0.08
    à¸Ĥาà¸Ķ
    -0.08
    è¡ĢèĦī
    -0.08
    оÑĢо
    -0.08
    POSITIVE LOGITS
    åIJİæĤĶ
    0.15
    转åıĺ
    0.14
     reconsider
    0.13
    å¤īãĤıãĤĭ
    0.13
    CHANGE
    0.13
    æĶ¹åıĺ
    0.13
    åıĺæĽ´
    0.12
    æĤĶ
    0.12
     change
    0.11
    å¤īãĤıãģ£ãģ¦
    0.11
    Activations Density 0.074%

    No Known Activations