© 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. 62360
    Prev
    Next
    INDEX
    Explanations

    struggle, entitled, able, capable

    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
    伤亡
    -0.10
    Į¨
    -0.09
    ]]></
    -0.09
    è¾Ľè¾£
    -0.09
    å¦Ĥä½ķåİ»
    -0.09
    romatic
    -0.09
    LOPT
    -0.09
    _CLI
    -0.08
    é¢Ĥ
    -0.08
    å°Ĩ士
    -0.08
    POSITIVE LOGITS
    çĶŁåij½åĬĽ
    0.10
    ä»İä¸ļèĢħ
    0.09
     itself
    0.08
    èĦ±ç¦»
    0.08
    ç»ıçIJĨ
    0.08
    主人
    0.08
    çĶŁæľº
    0.08
     its
    0.08
    å®ĥçļĦ
    0.08
    çݩ家æĿ¥è¯´
    0.08
    Activations Density 0.302%

    No Known Activations