© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19745
    Prev
    Next
    INDEX
    Explanations

    places and neighborhoods

    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¨åİ¿
    -0.14
    该åİ¿
    -0.11
     towns
    -0.11
    åİ¿éķ¿
    -0.11
    该æĿij
    -0.11
    åħ¨éķĩ
    -0.11
    å³Ĵ
    -0.10
    å¸Ĥåİ¿
    -0.10
    åİ¿åŁİ
    -0.10
    å°ıéķĩ
    -0.10
    POSITIVE LOGITS
    åľ¨å¹¿å·ŀ
    0.12
    çĸ³
    0.10
    è¡Ĺéģĵ
    0.10
    çIJĨ
    0.09
    thr
    0.09
    éĥ½å¸Ĥ
    0.09
    æĭīèIJ¨
    0.08
    éĽį
    0.08
    Sense
    0.08
    æĦŁè°¢
    0.08
    Activations Density 0.186%

    No Known Activations