© 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. 56410
    Prev
    Next
    INDEX
    Explanations

    nowhere to go

    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
     пÑĢоб
    -0.09
    çĦ±
    -0.09
    zej
    -0.09
    æıIJéĨĴ
    -0.09
    ä¸įéĻIJ
    -0.09
    å«Į
    -0.09
    æ®ĭ
    -0.09
    åĴ±
    -0.09
    å¹²éĥ¨éĺŁä¼į
    -0.09
    ç§ijæĬĢ大åѦ
    -0.08
    POSITIVE LOGITS
    æĹłæīĢ
    0.16
    åı¯ä¾Ľ
    0.13
     nowhere
    0.12
    åİ»åĵªéĩĮ
    0.10
    æľīäºĨ
    0.10
    engo
    0.10
    ä¾ĿéĿł
    0.10
     кÑĥда
    0.10
    æľīè¶³å¤ŁçļĦ
    0.10
    æĹłäºº
    0.10
    Activations Density 0.060%

    No Known Activations