© 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. 10589
    Prev
    Next
    INDEX
    Explanations

    easy to use

    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¸įåĩĨ
    -0.10
    è½°
    -0.09
    æīĩ
    -0.09
    åĩºåħ¥
    -0.09
    å®ķ
    -0.08
    .SERVER
    -0.08
    æľįåĬ¡èĥ½åĬĽ
    -0.08
    èµį
    -0.08
    çļĦåģļæ³ķ
    -0.08
    éĢģåĩº
    -0.08
    POSITIVE LOGITS
    åıĭ好
    0.13
    çķĮéĿ¢
    0.13
    æĺĵ
    0.10
     ease
    0.10
    .easy
    0.10
    :UI
    0.10
    缴è§Ĥ
    0.10
    æĩ¿
    0.10
    å¿«æį·
    0.10
    æŀģ
    0.10
    Activations Density 0.097%

    No Known Activations