© 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. 32152
    Prev
    Next
    INDEX
    Explanations

    engagement ring

    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
    ç¼ĩ
    -0.11
    åĬŀ
    -0.10
    妥
    -0.09
    åŃ¦å®¶
    -0.09
     еÑīÑij
    -0.08
     cry
    -0.08
    levator
    -0.08
    æģ¯
    -0.08
    常çĶ¨
    -0.08
     Tools
    -0.07
    POSITIVE LOGITS
    åIJ¯èĴĻ
    0.10
    .literal
    0.10
    èķ¨
    0.10
    ä¸įæħİ
    0.09
    款
    0.09
    ç«ŀéĢī
    0.09
    è¿ľæĻ¯
    0.09
    çIJĨç§ij
    0.09
    INAL
    0.09
    çĽĴ
    0.09
    Activations Density 0.006%

    No Known Activations