© 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. 8865
    Prev
    Next
    INDEX
    Explanations

    calling one another

    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
     SOM
    -0.10
     kuk
    -0.09
    fal
    -0.09
    è¿Ļ段æŶéĹ´
    -0.09
    æ³Ľ
    -0.09
    åģļè¿ĩ
    -0.09
    èIJ½åľ°
    -0.09
    ãģĹãģŁãģĵãģ¨
    -0.09
    æ¦Ń
    -0.08
    è¶ĭ
    -0.08
    POSITIVE LOGITS
     others
    0.10
    带åĬ¨
    0.10
     дÑĢÑĥгие
    0.09
    对æĸ¹
    0.09
    å¿ĥä¸Ń
    0.09
    ãģĿãĤĮãģ«
    0.08
    bung
    0.08
    others
    0.08
    éħįä¸Ĭ
    0.08
     sobie
    0.08
    Activations Density 0.603%

    No Known Activations