© 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. 35818
    Prev
    Next
    INDEX
    Explanations

    grandmother, mother, grandparents

    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
    é£İåIJ¹
    -0.09
    errat
    -0.09
    æ¼Ĥæµģ
    -0.09
    æ¼Ķç»İ
    -0.09
    é©°
    -0.09
    åĽ°æī°
    -0.09
    ä¸īåĽ½
    -0.08
    versed
    -0.08
     imprint
    -0.08
    éĢIJ
    -0.08
    POSITIVE LOGITS
    ç¥ĸçĪ¶
    0.10
    çĬ¹
    0.10
    ä¸ĢæīĢ
    0.09
    illes
    0.09
    è¹ī
    0.09
    å¤ĸå©Ĩ
    0.09
    诰
    0.09
    åģ·
    0.08
     кваÑĢÑĤиÑĢ
    0.08
    -held
    0.08
    Activations Density 0.011%

    No Known Activations