© 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. 35278
    Prev
    Next
    INDEX
    Explanations

    be placed or written

    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
    对åħ¶
    -0.12
    讲æķħäºĭ
    -0.10
    åĬŀäºĭ
    -0.10
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.10
    èµ·æĿ¥
    -0.10
    没æľī太大
    -0.10
    .nl
    -0.09
    对她
    -0.09
    åģļäºĭ
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    POSITIVE LOGITS
    æĶ¾åľ¨
    0.19
    æĶ¾åĪ°
    0.15
    éĢģåĪ°
    0.15
    æĶ¾åħ¥
    0.15
    转移åĪ°
    0.14
    移åĪ°
    0.14
    ç½®äºİ
    0.14
    åºĶçĶ¨äºİ
    0.13
    èIJ½åľ¨
    0.13
    åĩºçİ°åľ¨
    0.13
    Activations Density 0.463%

    No Known Activations