© 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. 17349
    Prev
    Next
    INDEX
    Explanations

    passing through or by

    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
    æĤŁ
    -0.10
    åĬĽæ°Ķ
    -0.10
    好äºĨ
    -0.10
    åĬŀ好
    -0.10
    aken
    -0.10
    Intern
    -0.09
    åħ¼ä»»
    -0.09
    趺
    -0.09
     intern
    -0.09
    è¦ģåģļ好
    -0.09
    POSITIVE LOGITS
    è·¯è¿ĩ
    0.24
     passing
    0.19
     Passing
    0.16
     passes
    0.14
    -pass
    0.14
    pass
    0.14
     pass
    0.14
     passer
    0.13
    (pass
    0.13
    éĢĶ
    0.12
    Activations Density 0.215%

    No Known Activations