© 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. 26892
    Prev
    Next
    INDEX
    Explanations

    The Bar Association

    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
    лив
    -0.09
    å®ŀçī©
    -0.09
    被æīĵ
    -0.08
    setting
    -0.08
    åĪĿè¡·
    -0.08
    庸
    -0.08
    ibo
    -0.08
    å¤Ħæĸ¹
    -0.08
    ulp
    -0.08
    åĽ½äºº
    -0.08
    POSITIVE LOGITS
    ä¾
    0.10
    æĹ¢æľī
    0.10
    ä¸įèĥ½åĨį
    0.09
    å¯Ĵ
    0.09
    æĹ¢èĥ½
    0.09
    详ç»Ĩä»ĭç»į
    0.09
    æĸ°æĹ¶æľŁ
    0.09
    带走
    0.08
    å¤ĸåľ°
    0.08
    æŁĵ
    0.08
    Activations Density 0.008%

    No Known Activations