© 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. 20624
    Prev
    Next
    INDEX
    Explanations

    intelligent followed by nouns

    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
    åĨ³å¿ĥ
    -0.10
     LIS
    -0.10
     flash
    -0.09
    åıijè¾¾åĽ½å®¶
    -0.08
    å¾Ĺèµ·
    -0.08
    éĴı
    -0.08
     Rebel
    -0.08
    ilia
    -0.08
    æ´²
    -0.08
     Tribe
    -0.08
    POSITIVE LOGITS
    æİĸ
    0.10
    åĢ¼çıŃ
    0.09
     Dexter
    0.09
    毫ä¸į
    0.09
    inct
    0.09
    зол
    0.08
    è·Ľ
    0.08
    lement
    0.08
    毫
    0.08
    ç»ĻåĬĽ
    0.08
    Activations Density 0.185%

    No Known Activations