© 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. 31599
    Prev
    Next
    INDEX
    Explanations

    part of proper names

    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
    åħ¨åĽ½äººæ°ij
    -0.10
    é©¿
    -0.09
    ocation
    -0.09
    Trap
    -0.09
     Ventura
    -0.08
    éĤł
    -0.08
    磬
    -0.08
    emarks
    -0.08
    ç¼°
    -0.08
    å®ŀä¹łçĶŁ
    -0.08
    POSITIVE LOGITS
    è°ģçŁ¥éģĵ
    0.08
    åįĥéĩĮ
    0.08
     обÑĥÑĩ
    0.08
    æĬĹæĪĺ
    0.08
    ar
    0.08
    æ´»è·ĥ
    0.08
    åĪĿæģĭ
    0.08
    åħļåĨħ
    0.07
    æ¾Ħ
    0.07
    çīºçī²
    0.07
    Activations Density 0.353%

    No Known Activations