© 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. 38685
    Prev
    Next
    INDEX
    Explanations

    cities in Pakistan

    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
    æĻ¦
    -0.10
    å¯Ħæīĺ
    -0.10
    .getMap
    -0.10
    çij¶
    -0.09
    ç¿»
    -0.09
    ä½ıäºĨ
    -0.09
    åıµ
    -0.08
    èĹı
    -0.08
    ä½ıåľ¨
    -0.08
    nev
    -0.08
    POSITIVE LOGITS
    å·´åŁºæĸ¯åĿ¦
    0.10
    éĥ½èĥ½å¤Ł
    0.09
    涿
    0.09
     Lahore
    0.09
    mad
    0.09
    entin
    0.09
     DN
    0.09
    éĢĥ
    0.09
    åĩ¡
    0.09
     Dickinson
    0.09
    Activations Density 0.085%

    No Known Activations