© 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. 32421
    Prev
    Next
    INDEX
    Explanations

    component or components

    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
    çijķ
    -0.10
     Patri
    -0.10
    atan
    -0.09
    ä»ħ代表
    -0.09
    yne
    -0.08
    ä¸įç®Ĺ
    -0.08
    elib
    -0.08
     eng
    -0.08
     Pant
    -0.08
     guid
    -0.08
    POSITIVE LOGITS
     aspect
    0.17
    éĥ¨ä»½
    0.15
    æĸ¹éĿ¢
    0.15
     aspects
    0.15
    aspect
    0.14
    éĥ¨åĪĨ
    0.13
     component
    0.13
     element
    0.12
    åħĥç´ł
    0.12
    çݯèĬĤ
    0.12
    Activations Density 0.086%

    No Known Activations