© 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. 62953
    Prev
    Next
    INDEX
    Explanations

    receive data or file

    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
    enko
    -0.10
    çŁ¾
    -0.10
    åĨĹ
    -0.09
    éļIJéļIJ
    -0.08
     запиÑģи
    -0.08
    rances
    -0.08
    _nh
    -0.08
    çħ½
    -0.08
     поп
    -0.08
    reme
    -0.08
    POSITIVE LOGITS
    .receive
    0.12
    æĶ¶åĪ°
    0.11
     ë°Ľ
    0.11
    ä¸įåĪ°
    0.10
    .Receive
    0.10
    æİ¥æĶ¶
    0.10
     ÑĢÑĭ
    0.09
    ë°Ľ
    0.09
    æĶ¶åĪ°äºĨ
    0.09
    лем
    0.09
    Activations Density 0.136%

    No Known Activations