© 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. 31443
    Prev
    Next
    INDEX
    Explanations

    environment

    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
    inel
    -0.10
    esis
    -0.09
    æĪĸå¤ļ
    -0.09
    _PD
    -0.09
    ses
    -0.08
    ä¼ļ让
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    毫
    -0.08
     impro
    -0.08
    orama
    -0.08
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.15
    è¿Ļæĺ¯æĪij
    0.11
    人士
    0.11
    åħ±åIJĮä½ĵ
    0.09
    åijĸ
    0.09
    клÑİÑĩи
    0.09
    çĺ©
    0.09
    æ¶ĪåĮĸ
    0.09
    ynth
    0.09
    åIJĮä»ģ
    0.08
    Activations Density 0.032%

    No Known Activations