© 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. 63187
    Prev
    Next
    INDEX
    Explanations

    emphasis or clarification

    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
    aju
    -0.10
     бÑĥд
    -0.10
    åĮ¾
    -0.10
    acker
    -0.09
    éĶĻ
    -0.09
    åħľ
    -0.09
    ught
    -0.09
     Sey
    -0.08
    ELY
    -0.08
    _pd
    -0.08
    POSITIVE LOGITS
    æīįæĺ¯çľŁæŃ£
    0.09
    ä¸įæ¸ħ
    0.09
    讵
    0.09
    å°±æĺ¯ä¸ºäºĨ
    0.09
     piston
    0.09
    usch
    0.09
    éºĴ
    0.09
    æĺ¯åĽłä¸º
    0.09
    ä¸įåĩºæĿ¥
    0.08
    äºĽä»Ģä¹Ī
    0.08
    Activations Density 0.019%

    No Known Activations