© 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. 58258
    Prev
    Next
    INDEX
    Explanations

    metal oxides

    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
    ä¸ī大
    -0.10
    人å¿ĥ
    -0.10
    è¿ĩå¾Ĺ
    -0.09
    ยà¸ģ
    -0.09
    å§ĵ
    -0.09
    matic
    -0.09
    è¿ĩçļĦ
    -0.09
    prite
    -0.09
    ä¸ĢéĿ¢
    -0.09
    moz
    -0.09
    POSITIVE LOGITS
    åIJĮä»ģ
    0.11
    åĥ§
    0.10
    篦
    0.10
     ná»Ļp
    0.09
    alking
    0.09
    çıł
    0.08
    ä»»æľŁ
    0.08
    hipster
    0.08
     ore
    0.08
    ç§īæī¿
    0.08
    Activations Density 0.168%

    No Known Activations