© 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. 19621
    Prev
    Next
    INDEX
    Explanations

    Avaya switch or IP telephony

    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
    åħ¥åĽŃ
    -0.09
    оÑģÑĤей
    -0.09
    串
    -0.09
    éķŃ
    -0.09
     Lewis
    -0.09
    æīĭèĦļ
    -0.09
    -Ta
    -0.09
    è´¹
    -0.08
    overe
    -0.08
    æŁ¥çľĭ详æĥħ
    -0.08
    POSITIVE LOGITS
    æīĺ
    0.10
    ä¸Ģå¤ľ
    0.09
    çĿ£åĬŀ
    0.08
    å¥ij
    0.08
    æĮ¤
    0.08
    æ³Ĭ
    0.08
    çĶŁèĤ²
    0.08
     beg
    0.08
    éĤ£æł·
    0.08
    tex
    0.07
    Activations Density 0.177%

    No Known Activations