© 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. 63451
    Prev
    Next
    INDEX
    Explanations

    Groovy, Grails, Scala programming

    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
    ä»Ģä¹Īåij¢
    -0.11
    ç¾½
    -0.10
    æ¸Ń
    -0.09
    æĺ¯ä¸įä¼ļ
    -0.09
    åĪ©çĶ¨çİĩ
    -0.08
    .pipe
    -0.08
    è¶ħæłĩ
    -0.08
    ads
    -0.08
    _THREADS
    -0.08
    .servers
    -0.08
    POSITIVE LOGITS
    çĮ´
    0.11
    èĢį
    0.09
    éŀĺ
    0.09
    ARED
    0.09
    SO
    0.09
    plets
    0.09
    rng
    0.09
     деÑĤей
    0.09
    主å¸ħ
    0.09
    èŀĤ
    0.09
    Activations Density 0.231%

    No Known Activations