© 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. 53546
    Prev
    Next
    INDEX
    Explanations

    activity

    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
    _logger
    -0.09
     réfé
    -0.09
     bif
    -0.08
    æĸ¼
    -0.08
     иÑģÑĤ
    -0.08
    èĪŀåı°ä¸Ĭ
    -0.08
    å®Ĺ
    -0.08
    çĪ±ç¾İ
    -0.08
    olid
    -0.08
    çľ¼åīį
    -0.08
    POSITIVE LOGITS
     obliv
    0.13
    å½Ģ
    0.12
    æľªçŁ¥
    0.12
    åĨįåĪ°
    0.11
     fray
    0.10
    æ·±å¤Ħ
    0.10
    误åĮº
    0.09
    /out
    0.09
    å°ı康社ä¼ļ
    0.09
    æĥ³åİ»
    0.09
    Activations Density 0.185%

    No Known Activations