© 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. 61957
    Prev
    Next
    INDEX
    Explanations

    conducting investigations or surveys

    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
    jec
    -0.11
    åĢŁçĶ¨
    -0.09
    ä¸Ģåı¥è¯Ŀ
    -0.09
    èĵĿåĽ¾
    -0.09
    éĢģä¸Ĭ
    -0.09
    GRAM
    -0.09
    ograf
    -0.09
    berman
    -0.09
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    -0.09
    воÑĢоÑĤ
    -0.09
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.10
    æľĪä¸ĭ
    0.10
    å¹¿æ³ĽçļĦ
    0.10
    éĩĩ访æŶ
    0.09
    åħ¨æĸ¹ä½į
    0.08
    å©Ĩ
    0.08
     thorough
    0.08
    ä¸įéĹ´æĸŃ
    0.08
    对èĩªå·±
    0.08
    çĭIJ
    0.08
    Activations Density 0.073%

    No Known Activations