© 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. 21564
    Prev
    Next
    INDEX
    Explanations

    venting or ventricular

    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
    岸边
    -0.11
    é½
    -0.10
    agi
    -0.10
    keit
    -0.10
    ission
    -0.09
    .endTime
    -0.09
    undi
    -0.09
    anka
    -0.08
     Manson
    -0.08
    éĢĢå¸Ĥ
    -0.08
    POSITIVE LOGITS
    åī¯ä¸»ä»»
    0.10
    ricular
    0.09
    ius
    0.09
    iations
    0.09
    YT
    0.09
    çªĹå¤ĸ
    0.09
    ôme
    0.09
    éĢĭ
    0.09
    lify
    0.09
    ä¹İ
    0.08
    Activations Density 0.028%

    No Known Activations