© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34994
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    æ²īæ·Ģ
    -0.09
    åıĺå¾ĹæĽ´åĬł
    -0.09
    ÙĪØ·
    -0.09
    åİĺ
    -0.09
    èĤ©
    -0.09
    ç²¥
    -0.09
    ondon
    -0.08
    ä½»
    -0.08
    éĵ¢
    -0.08
    locals
    -0.08
    POSITIVE LOGITS
    3
    0.11
    9
    0.10
    5
    0.10
    4
    0.10
    8
    0.10
    7
    0.10
    åIJİç»Ń
    0.10
    6
    0.09
    2
    0.09
     presses
    0.09
    Activations Density 0.047%

    No Known Activations