© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50807
    Prev
    Next
    INDEX
    Explanations

    pond brews, landscape, country

    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
    bart
    -0.10
    éħĭ
    -0.09
    ../../../
    -0.09
    骢
    -0.09
    most
    -0.09
    NAS
    -0.09
    éĺµå®¹
    -0.09
    dehyde
    -0.08
    compression
    -0.08
    ä»İ严治
    -0.08
    POSITIVE LOGITS
    amental
    0.12
    媳
    0.10
    exter
    0.10
    reeze
    0.10
    eur
    0.10
    ilet
    0.10
    side
    0.10
    æ°´éĩı
    0.09
     deliber
    0.09
    oodle
    0.09
    Activations Density 0.004%

    No Known Activations