© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20060
    Prev
    Next
    INDEX
    Explanations

    in a... way

    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
    å¾Ĺèµ·
    -0.10
    åī¯å±Ģéķ¿
    -0.10
    è¦ģæĺ¯
    -0.10
    çĶ¨æĿ¥
    -0.09
    ä½ľèĢħæīĢæľī
    -0.09
    æ´Ľåħĭ
    -0.09
    è¿Ļä¹Īåģļ
    -0.09
    _WRAP
    -0.08
    èĮ«èĮ«
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    åī§ä¸Ń
    0.09
    ä¸įå¼Ģ
    0.09
    åıĮèĦļ
    0.08
    åŁİéķĩ
    0.08
    å½»
    0.08
    ãģĬãģĭ
    0.08
    lessness
    0.08
    头åıij
    0.08
    鹧
    0.08
    orm
    0.08
    Activations Density 0.036%

    No Known Activations