© 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. 63210
    Prev
    Next
    INDEX
    Explanations

    virtual reality and Citrix

    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
     pet
    -0.10
    alis
    -0.09
    çŁ³æ²¹åĮĸå·¥
    -0.08
    åĩºåĽ½
    -0.08
    yla
    -0.08
    ä»İ严治
    -0.08
    çĶ²çĬ¶èħº
    -0.08
    pur
    -0.08
    getNode
    -0.08
     Pet
    -0.08
    POSITIVE LOGITS
    èĻļ
    0.10
    梦å¢ĥ
    0.09
    æĥħæĻ¯
    0.09
     VR
    0.08
    Helmet
    0.08
    æĹłè®ºå¦Ĥä½ķ
    0.08
    VR
    0.08
    梦
    0.08
     virtual
    0.08
    _virtual
    0.08
    Activations Density 0.089%

    No Known Activations