© 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. 62695
    Prev
    Next
    INDEX
    Explanations

    computer screens and usage

    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
     EAR
    -0.09
     QDir
    -0.09
    è¶ħé«ĺ
    -0.08
    åIJijè®°èĢħ
    -0.08
    麻
    -0.08
    å±IJ
    -0.08
    ä¸įå½±åĵį
    -0.08
     yık
    -0.08
    èĮĤ
    -0.08
    åħ¨åijĺ
    -0.08
    POSITIVE LOGITS
    å±ıå¹ķ
    0.20
     screen
    0.16
     ÑįкÑĢан
    0.15
    å±ıå¹ķä¸Ĭ
    0.13
    çľĭçĶµè§Ĩ
    0.13
     Screen
    0.12
    å±ı
    0.12
     computer
    0.12
    çĶµèĦij
    0.11
    .screen
    0.11
    Activations Density 0.066%

    No Known Activations