© 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. 53857
    Prev
    Next
    INDEX
    Explanations

    Toms Shoes, Oman

    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
    æĨ§
    -0.11
    å¼Ģæ°´
    -0.10
    äºĶå®ĺ
    -0.10
    é¢Ħå¤ĩ
    -0.09
    幸
    -0.09
    ocking
    -0.09
    pires
    -0.09
    å°»
    -0.09
    iesel
    -0.08
    aight
    -0.08
    POSITIVE LOGITS
    éĻħ
    0.09
    åıĤ
    0.09
     tl
    0.08
    é²ľ
    0.08
    encil
    0.08
    âĮ
    0.08
    鹫
    0.08
     Bowen
    0.08
     TL
    0.08
     Phillip
    0.08
    Activations Density 0.062%

    No Known Activations