© 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. 34479
    Prev
    Next
    INDEX
    Explanations

    same day / week / month

    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
    æģIJ
    -0.09
    LOTS
    -0.08
    éļ¾
    -0.08
    è¿ĺè®°å¾Ĺ
    -0.08
    erv
    -0.08
    etz
    -0.08
    åĮĻ
    -0.08
    èݲèĬ±
    -0.08
    aky
    -0.08
    ç²Ĺ
    -0.08
    POSITIVE LOGITS
    åĩłå¤©
    0.14
    ä¸Ģ段æŶéĹ´
    0.13
    æĹ¶æ®µ
    0.12
    åĩłå¹´
    0.12
    æľŁéĹ´
    0.12
    çŁŃçŁŃ
    0.12
    段æŶéĹ´
    0.12
    åĩłä¸ªæľĪ
    0.11
    æŶéĹ´åĨħ
    0.11
    ç¿Į
    0.10
    Activations Density 0.460%

    No Known Activations