© 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. 62817
    Prev
    Next
    INDEX
    Explanations

    Casablanca

    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
    ivalent
    -0.09
    æľĢéļ¾
    -0.09
    åĵģä½į
    -0.09
    spiel
    -0.09
    çĥĪ
    -0.09
    paces
    -0.08
    cry
    -0.08
    iffe
    -0.08
    own
    -0.08
    zie
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.10
    çİ»çĴĥ
    0.09
    åĶ¯æľī
    0.09
     ÐŀÐŀÐŀ
    0.09
    Glass
    0.09
    nev
    0.08
    åİ
    0.08
    æĬķèµĦ
    0.08
    zano
    0.08
    棵
    0.08
    Activations Density 0.001%

    No Known Activations