© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    government branches and officials

    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
    èı¹
    -0.10
    èĩ³äºİ
    -0.10
    иÑĢовки
    -0.09
    车éĹ´
    -0.09
    _EXTENDED
    -0.09
    å®īåħ¨æĦŁ
    -0.09
    çİ°è´§
    -0.09
    ä¸ŃåİŁ
    -0.09
    allery
    -0.09
    eneral
    -0.09
    POSITIVE LOGITS
    åĪĨæĶ¯
    0.10
     branches
    0.10
     judiciary
    0.10
    éĵ¨
    0.09
    åIJĦ级
    0.09
    ä¸ī家
    0.08
    .branch
    0.08
    Esc
    0.08
    æį¡
    0.08
    Branch
    0.08
    Activations Density 0.077%

    No Known Activations