© 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. 2450
    Prev
    Next
    INDEX
    Explanations

    screaming, ranting

    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
    ä¸Ģ種
    -0.12
    å¦ŀ
    -0.11
    ä¸Ģç§į
    -0.10
    èĩ³å°Ĭ
    -0.10
    åıijå±ķ模å¼ı
    -0.10
    åĪ¹éĤ£
    -0.10
    æĪijä¸įæĥ³
    -0.09
    è¿Ļä¸ĢåĪ»
    -0.09
    tion
    -0.09
    éĿł
    -0.09
    POSITIVE LOGITS
    满
    0.09
    ächt
    0.09
     полÑĥÑĩа
    0.09
    çĻ½èī²çļĦ
    0.08
    çĻ½èī²
    0.08
    ecz
    0.08
    ç¡ķ
    0.08
     Ramirez
    0.08
     Whole
    0.08
    æķ´
    0.08
    Activations Density 0.067%

    No Known Activations