© 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. 38191
    Prev
    Next
    INDEX
    Explanations

    more, less, enough, better, perfect

    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
    alink
    -0.11
    marvin
    -0.09
    æ²Ł
    -0.09
    èĭ«
    -0.09
     Sabha
    -0.09
    usc
    -0.09
    Painter
    -0.09
    å´ĸ
    -0.09
    ãģĦãģŁãĤī
    -0.08
    .Unsupported
    -0.08
    POSITIVE LOGITS
    åħ®
    0.11
    å£
    0.10
    对æѤ
    0.09
    zer
    0.09
    æ¿ĢçĥĪ
    0.09
    éĢīåĩº
    0.09
    æīĢä»¥åľ¨
    0.09
    çļĦåİŁåĪĻ
    0.08
    åľ¨è¿Ļ
    0.08
    éĥħ
    0.08
    Activations Density 0.040%

    No Known Activations