© 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. 49872
    Prev
    Next
    INDEX
    Explanations

    navigating or navigating through

    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
    arus
    -0.13
    ocation
    -0.10
    halb
    -0.09
    å¾ĹçĽĬ
    -0.09
    åł
    -0.09
    rack
    -0.09
    rug
    -0.08
    ality
    -0.08
    便äºİ
    -0.08
    çIJĨçĶ±
    -0.08
    POSITIVE LOGITS
    0.12
    æĸ°å½¢åĬ¿
    0.11
    èĩªå¦Ĥ
    0.11
    ä¸Ģçķª
    0.10
    åħ¶éĹ´
    0.10
    éļ¾åħ³
    0.10
    æĸ°ä¸ĸ纪
    0.09
    els
    0.09
    è¿Ļç§įæĥħåĨµ
    0.09
    ä¸Ģåľº
    0.09
    Activations Density 0.015%

    No Known Activations