© 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. 63484
    Prev
    Next
    INDEX
    Explanations

    coral reefs and marine life

    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
    ente
    -0.10
    rup
    -0.09
    ses
    -0.09
    éĴ£
    -0.09
    itics
    -0.09
    itarian
    -0.09
    åī¯å±Ģéķ¿
    -0.09
     intervening
    -0.09
    eton
    -0.09
    æ®Ĩ
    -0.08
    POSITIVE LOGITS
    alytics
    0.10
    ìłł
    0.09
    .hist
    0.09
    à¹ģà¸Ĺ
    0.09
    å·¥ä½ľèĢħ
    0.08
    quot
    0.08
    èĻ»
    0.08
    alez
    0.08
     Radi
    0.08
     Lei
    0.08
    Activations Density 0.007%

    No Known Activations