© 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. 23814
    Prev
    Next
    INDEX
    Explanations

    election years

    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
    å½ķåħ¥
    -0.10
    å°ĨæĮģç»Ń
    -0.09
    Paginator
    -0.09
    ä¸įæĽ¾
    -0.09
    nung
    -0.09
    西çľģ
    -0.09
    æĹ¥æĬ¥
    -0.08
    æijŃ
    -0.08
    ÑĤÑĮ
    -0.08
    游åĩ»
    -0.08
    POSITIVE LOGITS
    urr
    0.09
    æĵį
    0.09
    æĦļ
    0.09
    æĦļèł¢
    0.09
    ä¸įæĺİ
    0.09
    atoes
    0.08
    ä¸Ģç¯ĩ
    0.08
    vern
    0.08
    èĩ´åij½
    0.08
    AINS
    0.08
    Activations Density 0.199%

    No Known Activations