© 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. 2368
    Prev
    Next
    INDEX
    Explanations

    except for establishing

    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
    æģ¶å¿ĥ
    -0.10
    ä¸Ģåij³
    -0.10
     setInterval
    -0.09
    è¿Ļ份
    -0.09
    åı¯èĥ½åıijçĶŁ
    -0.09
    éĻī
    -0.09
     tÃł
    -0.09
    åħ¨å¥Ĺ
    -0.09
    åı¯ä¾Ľ
    -0.09
    izr
    -0.09
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.12
    ä¾ĭå¤ĸ
    0.11
    edException
    0.10
    æĢ¥æķij
    0.10
    æŃ£å½ĵ
    0.10
     Exceptions
    0.09
     emergencies
    0.09
    æĢ¥éľĢ
    0.09
    åIJĪçIJĨçļĦ
    0.09
     exceptions
    0.09
    Activations Density 0.076%

    No Known Activations