© 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. 62622
    Prev
    Next
    INDEX
    Explanations

    power line and regulated output

    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
     dip
    -0.10
    æĿĨ
    -0.09
    ICLE
    -0.09
    æĶ¹éĢł
    -0.08
    ihan
    -0.08
     lac
    -0.08
    ichel
    -0.08
    çĩİ
    -0.08
     Blow
    -0.08
     Dip
    -0.08
    POSITIVE LOGITS
    æĥĩ
    0.10
    æĻĥ
    0.09
    ç³Ł
    0.09
    ä¾ĽåºĶ
    0.09
    æĹłå¿§
    0.09
    ç©©
    0.09
    æĶ¯
    0.09
    IMS
    0.09
     commons
    0.09
    çIJIJ
    0.09
    Activations Density 0.129%

    No Known Activations