© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8205
    Prev
    Next
    INDEX
    Explanations

    focus on outcomes and satisfaction

    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
    ฯ
    -0.12
    depending
    -0.10
    ouis
    -0.10
    èĨ³
    -0.09
    imers
    -0.09
     Thi
    -0.09
    oftware
    -0.09
    пÑĥÑģÑĤ
    -0.09
    æĪijçļĦå¿ĥ
    -0.09
    _VM
    -0.09
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.14
    èĢĮéĿŀ
    0.13
    æİĴè¡Į
    0.11
     rather
    0.11
    ç»ĨèĬĤ
    0.10
    è¿Ļä¸ĢçĤ¹
    0.10
     behalf
    0.09
    PID
    0.09
     aspect
    0.09
     aspects
    0.09
    Activations Density 0.115%

    No Known Activations