© 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. 52894
    Prev
    Next
    INDEX
    Explanations

    year-old horses

    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
    éĿ¢åĮħ
    -0.10
    驾
    -0.09
    å¸Ń
    -0.09
    èĵ¼
    -0.08
     pint
    -0.08
    /format
    -0.08
    äºĨæĪijçļĦ
    -0.08
    mdl
    -0.08
    éĢĥ离
    -0.08
     اÙĦØ£ÙĨ
    -0.08
    POSITIVE LOGITS
    çĶ¨åľ°
    0.10
    è§ĦåĪĴ设计
    0.09
    æĿ¡ä¾ĭ
    0.09
    大æĪ·
    0.09
     tall
    0.09
    èĥİ
    0.09
     Colo
    0.08
     Nur
    0.08
    SB
    0.08
    ç½ijæ°ij
    0.08
    Activations Density 0.156%

    No Known Activations