© 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. 54088
    Prev
    Next
    INDEX
    Explanations

    concerts and tours

    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
     GAR
    -0.10
    æĹĭ
    -0.10
    isle
    -0.09
    åıĮåıĮ
    -0.08
    åĴĮ个人
    -0.08
    ä¸įå±ij
    -0.08
    rena
    -0.08
     JAN
    -0.08
    quip
    -0.08
     backstage
    -0.08
    POSITIVE LOGITS
    éĻIJå®ļ
    0.10
    åĿĤ
    0.09
    avl
    0.09
    utch
    0.09
    äºĨä»ĸçļĦ
    0.09
    æĭ±
    0.09
    大æłij
    0.09
    çĮ·
    0.09
    çĮ¿
    0.09
    ä¸Ŀ绸
    0.08
    Activations Density 0.116%

    No Known Activations