© 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. 31778
    Prev
    Next
    INDEX
    Explanations

    written permission or agreement

    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
    scopes
    -0.09
    apot
    -0.09
    apa
    -0.09
    åĮħ
    -0.09
    è®®æ¡Ī
    -0.08
    ìĤŃ
    -0.08
    uge
    -0.08
     пов
    -0.08
    è¾Ķ
    -0.08
     circumstance
    -0.08
    POSITIVE LOGITS
    ÑģÑĮ
    0.10
    åĬłå¼ºå¯¹
    0.09
    èĻİ
    0.09
    å¹´ä¸ŃåĽ½
    0.09
    china
    0.09
    beck
    0.09
     Opr
    0.09
    ä¸İæĹ¶ä¿±è¿Ľ
    0.09
    è°ģèĥ½
    0.09
    产çĶŁçļĦ
    0.08
    Activations Density 0.024%

    No Known Activations