© 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. 30125
    Prev
    Next
    INDEX
    Explanations

    demographic and personal characteristics

    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
    çĹħæ¯ĴæĦŁæŁĵ
    -0.08
    otech
    -0.08
    rish
    -0.08
    ingu
    -0.08
    èIJ¥æĶ¶
    -0.08
    1
    -0.08
    鸽
    -0.08
    åħ³ä¹İ
    -0.07
    .Serialize
    -0.07
    æµ·å¤ĸ
    -0.07
    POSITIVE LOGITS
    æı
    0.09
    çŃ¹èµĦ
    0.08
    åĽŀéģ¿
    0.08
    çĪ±ç¾İ
    0.08
    梢
    0.08
    \\/
    0.08
    andom
    0.08
    åįļæĸĩ
    0.08
    æ¯į亲
    0.08
    noÅĽci
    0.07
    Activations Density 2.421%

    No Known Activations