© 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. 36020
    Prev
    Next
    INDEX
    Explanations

    deemed beneficial or relevant

    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
    äºĨ解ä¸Ģä¸ĭ
    -0.09
    éĻĢ
    -0.09
    зал
    -0.09
    ARP
    -0.08
    注æĺİ
    -0.08
    veau
    -0.08
     огÑĢани
    -0.08
    ãģ£ãģ¡
    -0.08
    ron
    -0.08
    DDL
    -0.08
    POSITIVE LOGITS
    认为
    0.14
    è§īå¾Ĺ
    0.13
    éĥ½è®¤ä¸º
    0.12
    èªįçĤº
    0.12
     deemed
    0.11
    认å®ļ
    0.11
    éĥ½è§īå¾Ĺ
    0.10
    è¯Ħä¼°
    0.10
    æĪij们认为
    0.09
    åĪ¤å®ļ
    0.09
    Activations Density 0.075%

    No Known Activations