© 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. 57761
    Prev
    Next
    INDEX
    Explanations

    transport infrastructure and infrastructure operators

    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
     quán
    -0.11
    çŀ°
    -0.11
    ErrorException
    -0.09
    enti
    -0.09
    åĽ¢
    -0.09
     Kann
    -0.09
    pedia
    -0.09
    çĭŃ
    -0.09
    çĹĽ
    -0.09
    åľ°çĤ¹
    -0.09
    POSITIVE LOGITS
    é«ĺéĢŁåħ¬è·¯
    0.10
    ovel
    0.09
    大桥
    0.09
    è¯ķè¡Į
    0.09
    é»ij马
    0.09
    éĤĻ
    0.09
    å·¥ç¨ĭè´¨éĩı
    0.09
    æĿŃ
    0.09
    ä¸īæľŁ
    0.08
    äºĮæľŁ
    0.08
    Activations Density 0.275%

    No Known Activations