© 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. 2565
    Prev
    Next
    INDEX
    Explanations

    performance requirements or improvements

    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
    izr
    -0.10
    uro
    -0.10
    ikon
    -0.10
    one
    -0.09
    çĮĹ
    -0.09
    à¸Ńà¸Ļ
    -0.09
    è²Ķ
    -0.09
    ä¸Ģéģĵ
    -0.09
    å®ŀè®Ń
    -0.09
    äºŃ
    -0.08
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.09
    anga
    0.08
    åįĵè¶Ĭ
    0.08
    æĢ§åĴĮ
    0.08
    äºĮèĢħ
    0.08
    ä½ļ
    0.08
    alley
    0.08
    GA
    0.08
    第ä¸Ģå±Ĭ
    0.08
    å°¤
    0.08
    Activations Density 0.029%

    No Known Activations