© 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. 32035
    Prev
    Next
    INDEX
    Explanations

    transformation and changes

    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
    åħĪ天
    -0.10
    人å±ħ
    -0.09
    ned
    -0.09
    çĥ½
    -0.09
    æ¯ĶæĭŁ
    -0.09
    å½ĵãģ¦
    -0.09
     بÙħ
    -0.09
    ÑĤок
    -0.09
    å¾Ĺä½ı
    -0.09
     HOLDERS
    -0.09
    POSITIVE LOGITS
    (transform
    0.12
    转åŀĭ
    0.10
     transformations
    0.10
    转åıĺ
    0.09
    åıĺåĮĸ
    0.09
     Transformation
    0.09
    æīŃæĽ²
    0.09
     transformation
    0.09
    Occurred
    0.09
     transform
    0.09
    Activations Density 0.226%

    No Known Activations