© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    no idea, no experience, no restrictions

    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
    æľªå¿ħ
    -0.11
    èİ·å¾ĹæĽ´å¤ļ
    -0.11
    ä¸Ģä½į
    -0.09
    æĽ´å¿«
    -0.09
     okreÅĽ
    -0.09
     lắm
    -0.09
    æĽ´å¥½åľ°
    -0.09
    è£Ĥ
    -0.09
    ç±³ç²ī
    -0.09
    èĥĮä¸Ĭ
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
    çĶŁæ°Ķ
    0.10
    elman
    0.10
    åĩłä¹İ没æľī
    0.10
     whatsoever
    0.09
    ä¼ĺçĤ¹
    0.09
    åĩłä¹İæīĢæľī
    0.09
    çijĹ
    0.09
    æľīä»·åĢ¼çļĦ
    0.09
    åī©ä½Ļ
    0.08
    Activations Density 0.063%

    No Known Activations