© 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. 63028
    Prev
    Next
    INDEX
    Explanations

    Scholars, recipients, graduates, participants

    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
    æīĢæľī人éĥ½
    -0.09
    广大å¸Ĥæ°ij
    -0.09
    åħ¨æ°ij
    -0.09
    æĸ°åŀĭåĨłçĬ¶
    -0.09
    ç¬ı
    -0.09
    linger
    -0.08
    人ãģ¯
    -0.08
    è°ĭ
    -0.08
    jni
    -0.08
    UMMY
    -0.08
    POSITIVE LOGITS
    第äºĮæī¹
    0.10
    第ä¸Ģæī¹
    0.10
    éĹªçĶµ
    0.09
    鼷
    0.09
    éĢīåıĸ
    0.09
    à¸łà¸²à¸Ħ
    0.09
     Program
    0.08
    éģ´éĢī
    0.08
    éĢīå®ļ
    0.08
    AGO
    0.08
    Activations Density 0.083%

    No Known Activations