© 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. 52719
    Prev
    Next
    INDEX
    Explanations

    Active Directory and DNS integration

    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
    _HARD
    -0.09
    ç§į
    -0.09
    éĻĤ
    -0.09
     ìŬ
    -0.09
    ç¨Ĺ
    -0.09
     xúc
    -0.09
     Mori
    -0.09
     tiá»ģm
    -0.09
    plen
    -0.09
    odian
    -0.08
    POSITIVE LOGITS
    æ¤į
    0.08
    åľ°ä½į
    0.08
    é£İæļ´
    0.08
     storm
    0.08
    ores
    0.08
    åĽ¾ä¸º
    0.08
     Jail
    0.08
    æķĻ
    0.08
    7
    0.08
    交åıĭ
    0.08
    Activations Density 0.139%

    No Known Activations