© 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. 9030
    Prev
    Next
    INDEX
    Explanations

    people involved in incidents

    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
    Ãłnh
    -0.11
    女ç¥ŀ
    -0.10
    ç¼Ģ
    -0.10
    让ä»ĸ们
    -0.10
    让æĤ¨
    -0.10
    atter
    -0.10
    anter
    -0.09
    è¿Ļæł·æīįèĥ½
    -0.09
    éĴĹ
    -0.09
    ä½Ĩä»ĸ们
    -0.09
    POSITIVE LOGITS
    amer
    0.08
     provid
    0.08
     whose
    0.08
    iac
    0.08
    5
    0.08
    ifest
    0.08
    volent
    0.08
     named
    0.08
    atee
    0.08
    9
    0.08
    Activations Density 0.075%

    No Known Activations