© 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. 52339
    Prev
    Next
    INDEX
    Explanations

    long

    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
    åĹľ
    -0.10
    æIJı
    -0.10
    lac
    -0.10
    	TokenName
    -0.09
    inem
    -0.08
    _FLUSH
    -0.08
    æĺĶæĹ¥
    -0.08
    ãĤ¸ãĥ¼
    -0.08
    коÑĢ
    -0.08
    REA
    -0.08
    POSITIVE LOGITS
    ness
    0.13
    æµĩ
    0.10
    abouts
    0.09
    模èĮĥ
    0.09
    èķ´
    0.09
    åĸīåĴĻ
    0.09
    ube
    0.09
     Inch
    0.09
    NESS
    0.09
    å§Ķ
    0.09
    Activations Density 0.046%

    No Known Activations