© 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. 9761
    Prev
    Next
    INDEX
    Explanations

    in any case

    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
    ä»»ä½ķå½¢å¼ı
    -0.12
    åĵªæĢķæĺ¯
    -0.10
    çĶļèĩ³æĺ¯
    -0.09
    åį´è¢«
    -0.09
    åį»
    -0.09
    èµ°å¾Ĺ
    -0.08
     пÑĥ
    -0.08
    monds
    -0.08
    æ³¼
    -0.08
    éĩįè¦ģåİŁåĽł
    -0.08
    POSITIVE LOGITS
    reau
    0.10
    atie
    0.09
    ç¼Ń
    0.08
    lake
    0.08
    andle
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
    常年
    0.08
    æĹºåŃ£
    0.08
    èij±
    0.08
    _FMT
    0.08
    Activations Density 0.031%

    No Known Activations