© 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. 23002
    Prev
    Next
    INDEX
    Explanations

    confirmed that

    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
    ä½łè§īå¾Ĺ
    -0.12
    -0.10
    忽çĦ¶
    -0.09
    æĬĺ
    -0.09
    æīģ
    -0.09
    æĪijè§īå¾Ĺ
    -0.09
    ForResult
    -0.09
    éĢ¼
    -0.09
     Westbrook
    -0.08
    ì²ĺ
    -0.08
    POSITIVE LOGITS
    没éĶĻ
    0.13
    è¿Ļä¸ĢçĤ¹
    0.11
    è¯ģå®ŀ
    0.10
    æł¸å®ŀ
    0.10
     yes
    0.09
    æĹłçĸij
    0.09
     Indeed
    0.09
    å±ŀå®ŀ
    0.09
    ment
    0.09
    rb
    0.09
    Activations Density 0.020%

    No Known Activations