© 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. 58087
    Prev
    Next
    INDEX
    Explanations

    negative descriptors

    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
    èĢķèĢĺ
    -0.10
    没éĶĻ
    -0.09
    缸å½ĵ
    -0.09
    çĮĽçĦ¶
    -0.09
    åħ¨å®¶
    -0.09
    ç©¿ä¸Ĭ
    -0.09
    åı¥è¯Ŀ
    -0.09
    åİ©
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    çĭłçĭł
    -0.08
    POSITIVE LOGITS
    regor
    0.09
    adal
    0.09
    æij¸
    0.08
    åµİ
    0.08
    meld
    0.08
    ä¸īåĽĽ
    0.08
    SSI
    0.08
    æ±ľ
    0.08
    elong
    0.08
     meld
    0.08
    Activations Density 0.049%

    No Known Activations