© 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. 4359
    Prev
    Next
    INDEX
    Explanations

    draws and ties

    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
    çĿĢä»ĸ
    -0.08
    åĴĮä»ĸçļĦ
    -0.08
    vest
    -0.08
     either
    -0.08
    оÑĩно
    -0.08
    èĢĢ
    -0.08
    è®Ń
    -0.07
    æĢ»èµĦ产
    -0.07
     diss
    -0.07
     Andre
    -0.07
    POSITIVE LOGITS
    acy
    0.10
    roma
    0.09
    _GRA
    0.09
    åı¯è§ģ
    0.09
    èĵ¬
    0.09
    -duration
    0.09
    _FRAMEBUFFER
    0.09
     Horm
    0.09
    å¯Ħ
    0.09
    æ¿¡
    0.09
    Activations Density 0.016%

    No Known Activations