© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50829
    Prev
    Next
    INDEX
    Explanations

    gradually or slowly modifying actions

    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
    空åīį
    -0.11
    à¹Ħว
    -0.09
    å¹²äºĭ
    -0.09
    æ±Łæ¹ĸ
    -0.09
     fren
    -0.08
    å¿«éĢŁ
    -0.08
    å¯IJ
    -0.08
    å½¹
    -0.08
    溢
    -0.08
    _RG
    -0.08
    POSITIVE LOGITS
    ç¼ĵæħ¢
    0.21
    æħ¢æħ¢
    0.19
    ç¼ĵç¼ĵ
    0.18
    æ¸IJ
    0.18
    æħ¢æħ¢çļĦ
    0.18
     slowly
    0.17
    æħ¢æħ¢åľ°
    0.17
     gradual
    0.16
    slow
    0.15
    ä¸ĢçĤ¹çĤ¹
    0.15
    Activations Density 0.115%

    No Known Activations