© 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. 37337
    Prev
    Next
    INDEX
    Explanations

    collectively referred to as

    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
    åģļçļĦäºĭ
    -0.10
    ACES
    -0.09
    _ACL
    -0.09
    NotNil
    -0.09
    arness
    -0.09
    acen
    -0.09
    è²Į
    -0.08
    翱
    -0.08
    åѤ
    -0.08
     اÙĦØ®ÙĦ
    -0.08
    POSITIVE LOGITS
    éģĵçIJĨ
    0.10
    sav
    0.09
    çĻ¾å®¶
    0.08
    éĶ¤
    0.08
    å¾Ĺ好
    0.08
     GiriÅŁ
    0.08
    etr
    0.08
    åĦĴ
    0.08
    æĻķ
    0.08
     конеÑĩно
    0.08
    Activations Density 0.044%

    No Known Activations