© 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. 11739
    Prev
    Next
    INDEX
    Explanations

    WLAN wireless network

    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
    åĤ»
    -0.11
    æĿ¥çĶµ
    -0.10
    ç²®
    -0.10
    个åĪ«
    -0.10
    çī²
    -0.09
    éĽī
    -0.09
    arend
    -0.09
    ILA
    -0.09
    irus
    -0.09
    ç¾İå¦Ĩ
    -0.09
    POSITIVE LOGITS
    å¹½
    0.09
    èĽ®
    0.08
    åĿĢ
    0.08
    åĪ«äººçļĦ
    0.08
    æłĩçŃ¾
    0.08
    ç¿ķ
    0.08
    æľĪä¸Ń
    0.08
    èĩ´çĻĮ
    0.08
    hé
    0.08
    Haz
    0.08
    Activations Density 0.198%

    No Known Activations