© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52448
    Prev
    Next
    INDEX
    Explanations

    this is how

    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
    çĮ¿
    -0.10
    è¿Ļæł·çļĦè¯Ŀ
    -0.09
    éĥ½åľ¨
    -0.09
    çĢijå¸ĥ
    -0.09
    æľį
    -0.09
    æŦ
    -0.09
    çĶµä»·
    -0.08
    çIJ¬
    -0.08
    ç¼Ń
    -0.08
    çĿ«æ¯Ľ
    -0.08
    POSITIVE LOGITS
    eras
    0.09
    åĩºåľº
    0.09
    pping
    0.08
    çīŁ
    0.08
    éģİãģĶ
    0.08
    ç»Ŀ大å¤ļæķ°
    0.08
    åīįè¿Ľ
    0.08
    æŃ£å¸¸
    0.08
    QUIRE
    0.08
    quire
    0.08
    Activations Density 0.159%

    No Known Activations