© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50115
    Prev
    Next
    INDEX
    Explanations

    obtain a copy

    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
    çĥ¯
    -0.09
    WI
    -0.09
    ä¼ļ被
    -0.09
    åĽ½å®¶éĩįçĤ¹
    -0.09
    éģĵçIJĨ
    -0.09
    åĢĻ
    -0.09
    mlin
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    åIJĦçľģ
    -0.09
     Chall
    -0.08
    POSITIVE LOGITS
    ä¸į顾
    0.09
    onta
    0.09
     Bard
    0.09
    ä¹Łå°±æĺ¯
    0.08
    OLA
    0.08
    åĪĨåĪ«
    0.08
    çľĩ
    0.08
    èīºæľ¯
    0.08
    ç½ķè§ģ
    0.08
    æĤłæĤł
    0.08
    Activations Density 0.034%

    No Known Activations