© 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. 35943
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    -heading
    -0.10
    å¹²èĦĨ
    -0.09
    æĺŁæĺŁ
    -0.09
     Compiled
    -0.09
    å¸ĥç½®
    -0.08
    çīĮ
    -0.08
     illustr
    -0.08
    æ¡Ī
    -0.08
    èĩ³ä¸Ĭ
    -0.08
    ãĤľ
    -0.08
    POSITIVE LOGITS
    èıģ
    0.10
     Sah
    0.10
    åįĩåįİ
    0.09
     immobil
    0.09
    èµİ
    0.08
    ä½ľåĵģåĨħ容
    0.08
    zza
    0.08
    寿
    0.08
    ey
    0.08
    大åıij
    0.08
    Activations Density 0.047%

    No Known Activations