© 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. 4101
    Prev
    Next
    INDEX
    Explanations

    music

    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
    éĤ£ä¹Īå¤ļ
    -0.08
    è¥¿çº¢æŁ¿
    -0.08
    éĥ½ä¼ļæľī
    -0.08
    cle
    -0.08
    åı¸
    -0.08
    æĥ¹
    -0.08
    net
    -0.08
    ä¸Ģåı£æ°Ķ
    -0.08
    ophil
    -0.08
     Vo
    -0.08
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.12
    峪
    0.10
    çĮ¿
    0.09
    utzer
    0.09
    æľ¬èº«
    0.09
    PropertyParams
    0.09
    æľ¬èº«çļĦ
    0.09
    漪
    0.09
    æ´¼
    0.09
    _quest
    0.09
    Activations Density 0.024%

    No Known Activations