© 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. 56815
    Prev
    Next
    INDEX
    Explanations

    reviews and ratings

    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
     Serg
    -0.08
    èĩªæķij
    -0.08
    ograd
    -0.08
    åĨ»
    -0.08
    æľ¬å±Ĭ
    -0.08
    æµħ
    -0.08
    åĦĭ
    -0.08
    åĨ·åĨ»
    -0.08
    éĶŃ
    -0.08
    CreatedBy
    -0.07
    POSITIVE LOGITS
    éħ·
    0.11
    èªī
    0.10
    çļĦ羣å®ŀ
    0.10
    让æ¶Īè´¹èĢħ
    0.09
    æ¶Īè´¹èĢħ
    0.09
     WOM
    0.09
    _authenticated
    0.09
     thumbs
    0.09
    ä¸įåħ¬å¹³
    0.09
    å°ijæķ°
    0.09
    Activations Density 0.085%

    No Known Activations