© 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. 7157
    Prev
    Next
    INDEX
    Explanations

    Nationals, Nat, nationality

    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
    ammen
    -0.09
    èĢģ人家
    -0.09
    ered
    -0.09
    ä¸ŃåĽ½å¤§éĻĨ
    -0.09
    zilla
    -0.09
    çĤĴèĤ¡
    -0.09
    å³Ļ
    -0.08
    åĽ½å®ī
    -0.08
    åįĬå²Ľ
    -0.08
    OUSE
    -0.08
    POSITIVE LOGITS
    istic
    0.09
    piring
    0.09
    èĹĵ
    0.09
    |=↵
    0.08
    aring
    0.08
    или
    0.08
    窿
    0.08
    istically
    0.08
    ä¸Ģ线åŁİå¸Ĥ
    0.08
    ci
    0.08
    Activations Density 0.006%

    No Known Activations