© 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. 20792
    Prev
    Next
    INDEX
    Explanations

    ones that, ones with

    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
    ä¸Ģéĺµ
    -0.10
    ä¸Ģç³»åĪĹ
    -0.10
    ä¸ĢåĪĩ
    -0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.09
    ä¸Ģæĸ¹
    -0.09
    ä¸Ģç»ı
    -0.09
    ä¸ĢæŶ
    -0.09
    ä¸ĢèĪ¬äºº
    -0.08
    tes
    -0.08
     Craft
    -0.08
    POSITIVE LOGITS
    ike
    0.11
    ear
    0.10
    uckle
    0.10
    quare
    0.10
    ided
    0.10
    _Reference
    0.09
    queeze
    0.09
    游æĪıä¸Ń
    0.09
    elve
    0.09
    elves
    0.09
    Activations Density 0.010%

    No Known Activations