© 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. 3483
    Prev
    Next
    INDEX
    Explanations

    wrong or right

    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
    æĢİä¹Īçľĭ
    -0.09
    身å¤Ħ
    -0.09
    åĪĨåĮº
    -0.09
    äºĭåıij
    -0.09
    è¾¹ç¼ĺ
    -0.09
    åĬĽæ±Ĥ
    -0.09
     Sheldon
    -0.09
    /effects
    -0.09
     bÅĤ
    -0.09
    .SDK
    -0.09
    POSITIVE LOGITS
    odes
    0.09
    ä¸Ģåı£æ°Ķ
    0.08
    ãģ£ãģ±
    0.08
    kart
    0.08
     Kart
    0.07
    hr
    0.07
    æľīå¤ļä¹Ī
    0.07
    icle
    0.07
    èĬ±å¼Ģ
    0.07
     Karma
    0.07
    Activations Density 0.044%

    No Known Activations