© 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. 31382
    Prev
    Next
    INDEX
    Explanations

    gunfire

    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
    弩
    -0.14
    çĤ¸å¼¹
    -0.13
    unks
    -0.10
    æĪIJç«ĭäºĨ
    -0.10
    å¸Ĩ
    -0.10
    åIJ¸åħ¥
    -0.09
    èĩªè¡Į车
    -0.09
    ç¾½
    -0.09
    è¯ķ管
    -0.09
    åłª
    -0.09
    POSITIVE LOGITS
    éĺ¶
    0.09
    ines
    0.09
    aped
    0.09
    ä¸įæŃ»
    0.09
    综åIJĪä½ĵ
    0.09
    åı°éĺ¶
    0.08
    .setCursor
    0.08
     opr
    0.08
     Wall
    0.08
    ians
    0.08
    Activations Density 0.071%

    No Known Activations