© 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. 54333
    Prev
    Next
    INDEX
    Explanations

    long exposure photography

    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
    inal
    -0.10
    é«ĭ
    -0.09
    ologne
    -0.08
    åĵģä½į
    -0.08
    è··
    -0.08
    å§Ķ
    -0.08
    èĥ¡
    -0.08
    躬
    -0.08
    kil
    -0.08
    æݬ
    -0.08
    POSITIVE LOGITS
    åĨ»ç»ĵ
    0.09
    Bracket
    0.09
    ç¿¡
    0.08
     bracket
    0.08
    åĽº
    0.08
    OrDefault
    0.08
    éķ¿è¾¾
    0.08
    液
    0.08
    æĭįæijĦ
    0.08
     Bracket
    0.08
    Activations Density 0.060%

    No Known Activations