© 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. 9283
    Prev
    Next
    INDEX
    Explanations

    Easter

    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
    soever
    -0.11
    age
    -0.09
    sert
    -0.09
    errupt
    -0.09
    и
    -0.09
    ur
    -0.09
    ron
    -0.09
    ãģĵãģ¨ãģĮ
    -0.09
    erval
    -0.08
    irs
    -0.08
    POSITIVE LOGITS
    ä¸įçŁ¥ä¸įè§ī
    0.10
    lies
    0.10
    ly
    0.10
    สา
    0.10
    mente
    0.10
    ient
    0.10
    çĦ¶æĺ¯
    0.09
    IZED
    0.09
    IENT
    0.09
    lijke
    0.09
    Activations Density 0.008%

    No Known Activations