© 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. 49486
    Prev
    Next
    INDEX
    Explanations

    equal to

    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
    åħ³éĶ®æĺ¯
    -0.10
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.10
    acles
    -0.09
    vious
    -0.08
    ricks
    -0.08
    els
    -0.08
    ä¸Ģæŀ¶
    -0.07
    uge
    -0.07
     haya
    -0.07
    iegel
    -0.07
    POSITIVE LOGITS
    AndHashCode
    0.16
    æĪĸå¤ļ
    0.10
    ities
    0.10
    äºĴåĪ©
    0.10
    ä»Ģä¹Īåij¢
    0.10
    zeitig
    0.10
    itarian
    0.09
    ipping
    0.09
    -sized
    0.09
    /disable
    0.09
    Activations Density 0.095%

    No Known Activations