© 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. 26735
    Prev
    Next
    INDEX
    Explanations

    part 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
    èĬĤ
    -0.10
    aal
    -0.10
    æķĿ
    -0.09
    oran
    -0.09
    sted
    -0.09
    è¿Ļ群
    -0.09
    寰
    -0.08
    ç¾Ķ
    -0.08
    enced
    -0.08
    enze
    -0.08
    POSITIVE LOGITS
    stuff
    0.12
    ä¸Ģ段
    0.12
     stuff
    0.12
    éĥ¨åĪĨ
    0.11
    éĩı
    0.10
     Portions
    0.10
    odem
    0.10
    éĥ¨åĪĨåĨħ容
    0.10
    eness
    0.10
    éĥ¨ä»½
    0.10
    Activations Density 0.152%

    No Known Activations