© 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. 56191
    Prev
    Next
    INDEX
    Explanations

    signature and petition

    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
    æºIJæ³ī
    -0.10
    acam
    -0.09
    idata
    -0.09
    å£ķ
    -0.09
    æģļ
    -0.09
    .TestCase
    -0.09
    allon
    -0.09
    иде
    -0.09
    èĴ¹
    -0.08
    æĪIJè¯Ń
    -0.08
    POSITIVE LOGITS
    çŃ¾åIJį
    0.25
    çŃ¾åŃĹ
    0.24
     signature
    0.21
    çŃ¾ç½²
    0.21
     signatures
    0.21
    signature
    0.20
    .signature
    0.19
    (signature
    0.18
    çŃ¾ç½²äºĨ
    0.18
     Signature
    0.17
    Activations Density 0.041%

    No Known Activations