© 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. 4672
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    sez
    -0.10
    çĬģ
    -0.10
    acha
    -0.09
    etus
    -0.09
    SCR
    -0.09
    itta
    -0.08
    onia
    -0.08
    ety
    -0.08
    æ¯ķ
    -0.08
    etz
    -0.08
    POSITIVE LOGITS
     either
    0.14
    æľīä¸įåIJĮçļĦ
    0.13
    either
    0.13
     EITHER
    0.12
    è¦ģä¹Ī
    0.11
     Either
    0.10
    æľīæīĢä¸įåIJĮ
    0.10
    ä¸įåIJĮç¨ĭ度
    0.10
    åİ¥
    0.09
    éű
    0.09
    Activations Density 0.058%

    No Known Activations