© 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. 33389
    Prev
    Next
    INDEX
    Explanations

    needs and requirements

    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
    ic
    -0.09
    obel
    -0.08
    éĨª
    -0.08
    èĩ³æĸ¼
    -0.08
    hud
    -0.08
    åĵªéĩĮ
    -0.08
    è¡Ļ
    -0.08
     Anc
    -0.08
    mun
    -0.08
    ä¸į让
    -0.08
    POSITIVE LOGITS
    lessly
    0.19
    fully
    0.12
    ioned
    0.11
    æĹºçĽĽ
    0.10
    åģļçļĦäºĭ
    0.10
    /w
    0.10
    /use
    0.10
     знаÑĤÑĮ
    0.10
    åģļçļĦäºĭæĥħ
    0.10
    uset
    0.10
    Activations Density 0.113%

    No Known Activations