© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52160
    Prev
    Next
    INDEX
    Explanations

    Michigan legal and governmental entities

    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
    æŃī
    -0.10
    ed
    -0.09
    eenth
    -0.09
    ires
    -0.09
    Ñĥж
    -0.09
     GPLv
    -0.09
    Ùĭ
    -0.09
    è°Ĥ
    -0.08
    们
    -0.08
    MOTE
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.11
    ifest
    0.11
    çķĶ
    0.11
    naire
    0.10
    å°±ç®Ĺæĺ¯
    0.10
    toolbox
    0.10
    ãģĹãģ¾ãģĦ
    0.09
    åĪ°è¿ĻéĩĮ
    0.09
    .Assertions
    0.09
    aden
    0.09
    Activations Density 0.015%

    No Known Activations