© 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. 58282
    Prev
    Next
    INDEX
    Explanations

    redundant jobs

    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
    receipt
    -0.09
    lator
    -0.09
    ÑĹ
    -0.09
    éľīç´ł
    -0.09
    LEM
    -0.09
    ceipt
    -0.09
    ITHER
    -0.09
    irected
    -0.09
    对èĩªå·±çļĦ
    -0.08
    ä¸ĸ人
    -0.08
    POSITIVE LOGITS
    è£ģåijĺ
    0.14
    å²Ĺä½į
    0.11
    æ±ĤèģĮ
    0.09
    æĬļ
    0.09
    åĬ³åĬ¡æ´¾éģ£
    0.09
    å¤ļä½Ļ
    0.09
    å°±ä¸ļ
    0.09
    åģľäº§
    0.09
     jobs
    0.09
    åħ¨åijĺ
    0.09
    Activations Density 0.187%

    No Known Activations