© 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. 1727
    Prev
    Next
    INDEX
    Explanations

    yelling at me

    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
    оÑĨен
    -0.09
    笮
    -0.09
    asil
    -0.09
     ASF
    -0.09
    å¾®ç¬ij
    -0.09
    еÑĩен
    -0.08
    æĤĦçĦ¶
    -0.08
    çĽ
    -0.08
    è¹Ļ
    -0.08
     Miche
    -0.08
    POSITIVE LOGITS
    åı£åı·
    0.12
    åĸĬ
    0.12
    éķĿ
    0.10
    apult
    0.10
    èĢĮåĩº
    0.10
    ãģ£ãģ±
    0.09
    äºĨåĩºæĿ¥
    0.09
    åĻª
    0.09
    æĸ©
    0.09
    åħ¬ç¤º
    0.09
    Activations Density 0.034%

    No Known Activations