© 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. 52442
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    æĬĹä½ĵ
    -0.09
    æŃ£è§Ħ
    -0.09
    以æѤ
    -0.08
    å±ĬæŶ
    -0.08
    enberg
    -0.08
    elm
    -0.08
    çļĦç¨ĭ度
    -0.08
    ï½¥
    -0.08
     prio
    -0.08
    åľ¨æĪijçľĭæĿ¥
    -0.08
    POSITIVE LOGITS
    åIJŀ
    0.12
     вÑĭÑĪе
    0.11
     above
    0.11
    åĪļæīį
    0.10
    åīįéĿ¢
    0.10
    ä¸Ĭè¿°
    0.10
    åīįæīĢ
    0.10
    igel
    0.09
     ниже
    0.09
    èĢģåŃIJ
    0.09
    Activations Density 0.139%

    No Known Activations