© 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. 62732
    Prev
    Next
    INDEX
    Explanations

    as, like, although

    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
    however
    -0.10
    åijĬè¯īä»ĸ
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    ding
    -0.09
    è´
    -0.09
    -kind
    -0.08
    ä¹ĭ乡
    -0.08
    aison
    -0.08
     بÙĬ
    -0.08
    ãĥĸãĥ©
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.09
    ä¹ĥèĩ³
    0.09
    åĽłä¸ºæĪij
    0.08
    åīĸ
    0.08
    åħ»
    0.08
    å®ĥæĺ¯
    0.08
    æĪij们éĥ½
    0.08
     TODO
    0.08
    udi
    0.07
    lest
    0.07
    Activations Density 0.144%

    No Known Activations