© 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. 29848
    Prev
    Next
    INDEX
    Explanations

    ldap and active directory services

    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
    çľĭ好
    -0.12
    åīįæıIJæĺ¯
    -0.10
    åĽ½åºĨ
    -0.10
    åīįæıIJ
    -0.09
    å¼Ģåĩº
    -0.09
    erie
    -0.09
    ä¿Ŀéļľ
    -0.08
    è¿ĻæĿ¡è·¯
    -0.08
    æŶæĬ¥
    -0.08
     Wald
    -0.08
    POSITIVE LOGITS
    ldap
    0.11
    çĹĽèĭ¦
    0.10
    nds
    0.10
    uzzi
    0.09
    åŁŁ
    0.09
    èľ»
    0.09
     dialect
    0.08
    isia
    0.08
    oter
    0.08
    ToProps
    0.08
    Activations Density 0.072%

    No Known Activations