© 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. 17657
    Prev
    Next
    INDEX
    Explanations

    Taj Mahal, Tatarstan, tartrazine

    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
    æĩĴ
    -0.10
    空æ°Ķè´¨éĩı
    -0.10
    åħ»èĢģä¿ĿéĻ©
    -0.10
    é³Ł
    -0.09
    /themes
    -0.09
    éĿĽ
    -0.09
    ç»ĪçĶŁ
    -0.09
    æľīæĦı
    -0.09
    ç¾İæĦŁ
    -0.09
    è¿Ľåľº
    -0.09
    POSITIVE LOGITS
    ANI
    0.10
    cri
    0.09
    ani
    0.08
    çīº
    0.08
    pw
    0.08
    èĻļåģĩ
    0.08
    pell
    0.08
     sharpen
    0.08
    anni
    0.08
    Shar
    0.08
    Activations Density 0.062%

    No Known Activations