© 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. 22804
    Prev
    Next
    INDEX
    Explanations

    Sarasota County Beach

    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
     lég
    -0.09
    ively
    -0.09
    å²ģ
    -0.08
    åºĭ
    -0.08
     pros
    -0.08
    /math
    -0.08
    æľ¬ç½ijç«Ļ
    -0.08
    ì§ĵ
    -0.08
    lessness
    -0.08
    askan
    -0.07
    POSITIVE LOGITS
    onet
    0.10
    awe
    0.10
    ç¾Ķ
    0.09
    ضة
    0.09
    _STS
    0.09
    æĪĴ
    0.09
    ç²ij
    0.09
    æĥħ趣
    0.08
    éĥ¨åĪĨåĨħ容
    0.08
    å·§åħĭåĬĽ
    0.08
    Activations Density 0.002%

    No Known Activations