© 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. 54798
    Prev
    Next
    INDEX
    Explanations

    internet history

    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
    æİĬ
    -0.08
    æĭħ
    -0.08
     chim
    -0.08
    .assets
    -0.08
    edium
    -0.08
    stadt
    -0.08
    ä¾Ľç»Ļ
    -0.08
     IDD
    -0.08
    mant
    -0.07
    è¡Ĺéģĵ
    -0.07
    POSITIVE LOGITS
    ALLY
    0.11
    å¦Ļ
    0.11
    orial
    0.10
    ìĥģ
    0.09
    æ·±å¤Ħ
    0.09
    tester
    0.09
    æ±īæĹı
    0.09
    ally
    0.09
    ually
    0.09
     ÑģÑĤал
    0.09
    Activations Density 0.033%

    No Known Activations