© 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. 54662
    Prev
    Next
    INDEX
    Explanations

    ball game pitches card BB

    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
    è¿Ļæĺ¯åĽłä¸º
    -0.09
    西æ¹ĸ
    -0.09
    ä¼ļ对
    -0.09
     JL
    -0.08
    ANO
    -0.08
    éĺģ
    -0.08
    ÑĢÑİ
    -0.08
    åıĸ代
    -0.08
    .hr
    -0.08
    ry
    -0.08
    POSITIVE LOGITS
    راس
    0.09
    å¢ŀè¿Ľ
    0.09
     Miche
    0.09
    éŀħ
    0.09
    entai
    0.08
    çĸ¹
    0.08
    幡
    0.08
    积æŀģå¼Ģå±ķ
    0.08
    åħ±åĴĮ
    0.08
    веÑģÑĤ
    0.08
    Activations Density 0.004%

    No Known Activations