© 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. 5054
    Prev
    Next
    INDEX
    Explanations

    offline, physical, download

    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
    æľ«
    -0.09
    okin
    -0.08
    agi
    -0.08
    è¾¹ä¸Ĭ
    -0.08
    é¢ĺæĿIJ
    -0.08
    æł¹
    -0.08
    å¥Ĺ
    -0.08
    rous
    -0.08
    /photos
    -0.08
    éŃĤ
    -0.08
    POSITIVE LOGITS
    线ä¸ĭ
    0.19
    å®ŀä½ĵåºĹ
    0.17
    纸质
    0.17
    offline
    0.16
    å®ŀçī©
    0.15
     offline
    0.15
    çİ°å®ŀçĶŁæ´»
    0.14
    å®ŀåľ°
    0.13
     physical
    0.13
     Offline
    0.13
    Activations Density 0.154%

    No Known Activations