© 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. 57675
    Prev
    Next
    INDEX
    Explanations

    place 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
    Multiplicity
    -0.09
    åıĺçİ°
    -0.08
    æĵį
    -0.08
    å¾ģæ±Ĥ
    -0.08
    æĻı
    -0.08
    é©Ń
    -0.08
    êu
    -0.08
    ģ
    -0.08
    润æ»ij
    -0.08
    åįĸæİī
    -0.08
    POSITIVE LOGITS
    积累äºĨ
    0.09
    asant
    0.09
    Gro
    0.08
    Union
    0.08
    inch
    0.08
    å¡ĺ
    0.08
    lick
    0.08
     stom
    0.08
    igator
    0.08
    å¤ļäºĨ
    0.08
    Activations Density 0.056%

    No Known Activations