© 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. 47990
    Prev
    Next
    INDEX
    Explanations

    click and try to do something

    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
    UNT
    -0.10
    为èĩªå·±
    -0.09
    é»İæĺİ
    -0.09
    ç½ķ
    -0.09
    åĮ»ç§ij
    -0.09
    ç¨Ģ
    -0.09
    /at
    -0.09
    éħ½
    -0.09
    ãĤĦãģ¯ãĤĬ
    -0.08
    åIJ¬è¯Ŀ
    -0.08
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.11
    è¶Ĭå¤ļ
    0.11
    íķĺëĬĶëį°
    0.10
    æĺİæĺİ
    0.10
    ãģĮãģĤãģ£ãģ¦
    0.10
    ä¸Ģè¶Ł
    0.09
    å¤ĸè§Ĥ
    0.09
    åį»
    0.09
    åIJİ
    0.09
    ä¸Ģç»ı
    0.09
    Activations Density 0.244%

    No Known Activations