© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38137
    Prev
    Next
    INDEX
    Explanations

    postal service and zip codes

    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
    elor
    -0.09
    ety
    -0.09
    èĢģå¦Ī
    -0.09
    æŶæŶ
    -0.09
    大æ´ĭ
    -0.09
    енÑĮ
    -0.08
    æķĻç»ĥ
    -0.08
     Pet
    -0.08
    ç»Ħéķ¿
    -0.08
    çIJĨäºĭéķ¿
    -0.08
    POSITIVE LOGITS
    lav
    0.10
    åĵ¡
    0.09
    aub
    0.09
    EMS
    0.09
    .assertIsInstance
    0.08
    è¹²
    0.08
    caught
    0.08
    ä½ĵåĪ¶æĶ¹éĿ©
    0.08
    åIJĮä»ģ
    0.08
    ">#
    0.08
    Activations Density 0.011%

    No Known Activations