© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    to be + qualifier

    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
    arak
    -0.09
    dek
    -0.09
    rog
    -0.09
    çļĦçĭ¬çī¹
    -0.09
    rolled
    -0.08
    é¹ij
    -0.08
    è¦ģä¹Ī
    -0.08
    irmed
    -0.08
    éłĵ
    -0.08
    æŃ£å¥½
    -0.08
    POSITIVE LOGITS
    éĢģå¾Ģ
    0.10
    询
    0.09
    åıijå±ķéĺ¶æ®µ
    0.09
    èĽĬ
    0.09
    çIJĨ解åĴĮ
    0.09
     Byrne
    0.09
    åģ¥åº·äº§ä¸ļ
    0.08
    á»ģ
    0.08
    chant
    0.08
    好çļĦ
    0.08
    Activations Density 0.011%

    No Known Activations