© 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. 33879
    Prev
    Next
    INDEX
    Explanations

    orangutan, sloths, boas, ballet, koalas

    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
    ulas
    -0.11
    åħ³åĪĩ
    -0.10
    æĸ°ä¸ŃåĽ½
    -0.09
    èŁ¹
    -0.09
    åīįåĪĹ
    -0.09
    åľ°å¸¦
    -0.09
    æ·ĺ
    -0.08
    象
    -0.08
    éĽ·è¾¾
    -0.08
    Soon
    -0.08
    POSITIVE LOGITS
    ç¹ĩ
    0.10
    CLU
    0.09
    ä¸Ģ棵
    0.09
    娲
    0.09
    严éĩį
    0.09
    å¨ĵ
    0.08
    åĽ½ãģ®
    0.08
    setImage
    0.08
    igator
    0.08
    顾
    0.08
    Activations Density 0.037%

    No Known Activations