© 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. 17192
    Prev
    Next
    INDEX
    Explanations

    ranking or first place

    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
    leh
    -0.09
    èĪ¹åıª
    -0.09
    çħľ
    -0.09
    lys
    -0.09
    åľ°çĭ±
    -0.08
    edin
    -0.08
    æŃ£åľ¨è¿Ľè¡Į
    -0.08
    <![
    -0.08
    å®ŀæķĪ
    -0.08
    çĵ¶
    -0.08
    POSITIVE LOGITS
    å½ĵä¹ĭæĹłæĦ§
    0.11
    ä¸įçķĻ
    0.11
    -ever
    0.09
    (@(
    0.09
    æ³±
    0.09
    ä¸Ģ天
    0.09
    alles
    0.09
     Brace
    0.09
    erta
    0.08
    大åŁİå¸Ĥ
    0.08
    Activations Density 0.029%

    No Known Activations