© 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. 30083
    Prev
    Next
    INDEX
    Explanations

    court case captions

    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
    ÑĢаг
    -0.09
    çĨŁ
    -0.08
    gap
    -0.08
     Lager
    -0.08
    êµIJ
    -0.08
    abar
    -0.08
    rib
    -0.08
    alu
    -0.07
    丰å¯ĮçļĦ
    -0.07
    ovel
    -0.07
    POSITIVE LOGITS
    æĪij们ä¼ļ
    0.09
    ç»ıéĶĢåķĨ
    0.09
    IOUS
    0.09
    纷纷
    0.09
    iphy
    0.08
    åĩ±
    0.08
    æī¾
    0.08
    çľĭä¸įåĩº
    0.08
    iously
    0.08
    éĺ³åı°
    0.08
    Activations Density 0.196%

    No Known Activations