© 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. 33754
    Prev
    Next
    INDEX
    Explanations

    comparison and similarities

    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
    èķĬ
    -0.09
    athe
    -0.09
    çĵ¢
    -0.09
    éĿ¶
    -0.08
    >Show
    -0.08
    udi
    -0.08
    åIJĮçŃī
    -0.08
    欲
    -0.08
    ìĤ´
    -0.08
    astery
    -0.08
    POSITIVE LOGITS
     similarities
    0.11
     parallels
    0.11
    对çħ§
    0.10
    缸éĢļ
    0.10
    渺
    0.10
    é¾Ł
    0.09
     comparing
    0.09
    æķĻè®Ń
    0.09
    SURE
    0.08
    ä¹ĭå¤Ħ
    0.08
    Activations Density 0.070%

    No Known Activations