© 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. 30805
    Prev
    Next
    INDEX
    Explanations

    making up or creating

    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
    urst
    -0.09
    phasis
    -0.09
    dsp
    -0.08
    æľ¬èĥ½
    -0.08
    dj
    -0.08
    AMP
    -0.08
     Ner
    -0.08
    1
    -0.08
     ink
    -0.08
    letic
    -0.07
    POSITIVE LOGITS
    èĻļåģĩ
    0.12
    åħ¨æĸ°çļĦ
    0.11
    åıijæĺİ
    0.11
    è¿İåIJĪ
    0.10
    åĪĽéĢłåĩº
    0.10
    è¡¥é½IJ
    0.10
    æĸ°çļĦ
    0.10
     invent
    0.10
    为èĩªå·±
    0.10
    vented
    0.10
    Activations Density 0.041%

    No Known Activations