© 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. 9702
    Prev
    Next
    INDEX
    Explanations

    utility company infrastructure

    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
    rong
    -0.10
    ÙĪرÙĪ
    -0.10
    /goto
    -0.10
    åºĬä½į
    -0.09
    éĬ·
    -0.09
    座ä½į
    -0.09
    éĶĢæ¯ģ
    -0.09
    åİ®
    -0.09
    åĨħå¿ĥçļĦ
    -0.09
    éĢĹ
    -0.09
    POSITIVE LOGITS
    ç©¿è¶Ĭ
    0.12
    çĩĥæ°Ķ
    0.11
    çĶµç½ij
    0.11
    åŁĭ
    0.10
    ä¸Ģæł¹
    0.10
    çħ¤æ°Ķ
    0.09
    Inline
    0.09
    ä¸ĢèĤ¡
    0.09
     eas
    0.09
    çĶµåĬĽ
    0.09
    Activations Density 0.080%

    No Known Activations