© 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. 57120
    Prev
    Next
    INDEX
    Explanations

    alcohol, laptop, computer, food, milk, boxed items

    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
    fte
    -0.09
    çĭĤ
    -0.09
    éĢļè¡Į
    -0.09
    å¼Ħ
    -0.09
    æ··ä¹±
    -0.09
    appe
    -0.09
    _OPERATOR
    -0.09
    å£ħ
    -0.08
    æĦīæĤ¦
    -0.08
    ams
    -0.08
    POSITIVE LOGITS
    ä¸įçĶĺ
    0.09
    ç±»
    0.09
    éĿ¢åŃIJ
    0.09
    åģķ
    0.09
    åıĬåħ¶ä»ĸ
    0.09
     boxed
    0.09
    åħ¥å¢ĥ
    0.08
    类产åĵģ
    0.08
     Fit
    0.08
    æķ°éĩı
    0.08
    Activations Density 0.189%

    No Known Activations