© 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. 17768
    Prev
    Next
    INDEX
    Explanations

    first glance

    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
     ÑıзÑĭк
    -0.10
    incy
    -0.10
    RIES
    -0.10
    éļĨ
    -0.09
    åħ¬ç§¯
    -0.09
    iggins
    -0.09
    letics
    -0.09
     erot
    -0.09
    /goto
    -0.09
    ä¾Ľå¤§å®¶
    -0.09
    POSITIVE LOGITS
    èĬĻèĵī
    0.09
    çIJĨ
    0.09
    æĿĨ
    0.08
    çī§
    0.08
    ew
    0.08
     Larson
    0.08
    éļıå¤Ħ
    0.08
    èļ¤
    0.08
     chá
    0.08
    ä»İæĿ¥æ²¡
    0.08
    Activations Density 0.003%

    No Known Activations