© 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. 63027
    Prev
    Next
    INDEX
    Explanations

    in conjunction with

    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
    иÑĩеÑģки
    -0.11
    èĪĽ
    -0.09
    èĿĹ
    -0.09
    è¯Ŀ说
    -0.09
    æµ·éĩı
    -0.09
    owing
    -0.09
    çĪ¬ä¸Ĭ
    -0.08
    à¸Ħวาม
    -0.08
    otope
    -0.08
    羣åĪĩ
    -0.08
    POSITIVE LOGITS
    eur
    0.09
    å§Ĭ妹
    0.09
    ç¾İæĻ¯
    0.08
    çĽĨåľ°
    0.08
    leur
    0.08
    ively
    0.08
    éĺħ读åħ¨æĸĩ
    0.08
    顼
    0.08
    upp
    0.08
    iso
    0.08
    Activations Density 0.021%

    No Known Activations