© 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. 38478
    Prev
    Next
    INDEX
    Explanations

    start with progression

    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
    é«ĺéĢŁ
    -0.08
    _EPS
    -0.08
    åIJ¦
    -0.08
    å¿ĺè®°äºĨ
    -0.08
    uplicate
    -0.08
     доÑģÑĤ
    -0.08
    _MATERIAL
    -0.08
    ressed
    -0.08
    泡
    -0.08
     Lanc
    -0.08
    POSITIVE LOGITS
    éĢIJæŃ¥
    0.17
    æħ¢æħ¢
    0.15
    åħĪ
    0.14
    éĢIJæ¸IJ
    0.14
    æ¸IJ
    0.14
    æħ¢æħ¢çļĦ
    0.14
    æħ¢æħ¢åľ°
    0.13
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.13
     gradual
    0.13
     gradually
    0.12
    Activations Density 0.054%

    No Known Activations