© 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. 58632
    Prev
    Next
    INDEX
    Explanations

    mythology and ancient texts

    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
    ater
    -0.09
     Rally
    -0.09
    acer
    -0.09
    è£ģå®ļ
    -0.08
     indoors
    -0.08
    enna
    -0.08
    ÅĽcie
    -0.08
    åī½
    -0.08
    èĩĢ
    -0.08
    Ùħت
    -0.08
    POSITIVE LOGITS
    æģ¬
    0.12
     Atlantis
    0.09
    ä»Ļå¢ĥ
    0.09
    æŃ£åĵģ
    0.09
     Lost
    0.09
    é£İæ°´
    0.09
    åµĽ
    0.09
    åŀĥåľ¾
    0.09
    è¿Ļä¸ªåľ°åĽ¾
    0.09
    éĽ¯
    0.09
    Activations Density 0.062%

    No Known Activations