© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    profits go to

    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
    å¹Ħ
    -0.09
    举
    -0.09
     raj
    -0.08
    aces
    -0.08
     Garland
    -0.08
    çķ²
    -0.08
    åij½
    -0.07
    åİŁæĿ¥æĺ¯
    -0.07
     ramp
    -0.07
    åĩºçİ°äºĨ
    -0.07
    POSITIVE LOGITS
    å³Ĵ
    0.10
    atee
    0.09
    (Channel
    0.09
    大éĥ¨åĪĨ
    0.09
    æŃ£çīĪ
    0.09
    家ãģ®
    0.09
     quad
    0.09
    åħħå®ŀ
    0.09
    ëĭĪëĭ¤
    0.09
    otropic
    0.09
    Activations Density 0.021%

    No Known Activations