© 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. 50076
    Prev
    Next
    INDEX
    Explanations

    subsequent followed by noun

    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
    æĺĶæĹ¥
    -0.11
    ä¸ĢæŶ
    -0.10
    çİ°åľ¨å·²ç»ı
    -0.10
    å¹³æŶ
    -0.10
    ou
    -0.10
    ahas
    -0.10
    ports
    -0.10
    æľĢçµĤ
    -0.10
    estate
    -0.10
    -0.10
    POSITIVE LOGITS
    ively
    0.11
    ãĤį
    0.11
    /current
    0.10
    -generation
    0.10
    ä¸įä¹ħ
    0.10
    ë¡ł
    0.09
    ä¼Ĭæĭī
    0.09
    ality
    0.09
    ment
    0.09
    strain
    0.09
    Activations Density 0.024%

    No Known Activations