© 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. 38612
    Prev
    Next
    INDEX
    Explanations

    entering a place or destination

    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
    CADE
    -0.10
    овиÑĩ
    -0.09
    ÑģÑĤавка
    -0.09
    isle
    -0.09
    missão
    -0.09
    chè
    -0.09
    ä¸Ģ身
    -0.09
    å·¥ç¨ĭæĬĢæľ¯
    -0.08
    èľ¥
    -0.08
    apyrus
    -0.08
    POSITIVE LOGITS
    è´º
    0.09
    eer
    0.09
    çīĩåŃIJ
    0.08
     Gear
    0.08
    gear
    0.08
    åŁİéĩĮ
    0.08
    èµĺ
    0.08
    åİ¿åŁİ
    0.08
    èµĦ
    0.08
     gear
    0.08
    Activations Density 0.034%

    No Known Activations