© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19911
    Prev
    Next
    INDEX
    Explanations

    against other or competing

    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
    à¸Ĺย
    -0.09
    éĴĿ
    -0.09
    èĬ±å¼Ģ
    -0.09
    Ñĭм
    -0.09
    å¯ħ
    -0.08
    èĪįå¾Ĺ
    -0.08
    -Y
    -0.08
    å¤įåħ´
    -0.08
    èĶļ
    -0.08
    èĬĹ
    -0.08
    POSITIVE LOGITS
    对æĬĹ
    0.21
     against
    0.18
    against
    0.17
    Against
    0.17
    æĬĹè¡¡
    0.16
    è¾ĥéĩı
    0.16
    对æīĭ
    0.14
     Against
    0.14
     пÑĢоÑĤив
    0.14
    对åĨ³
    0.14
    Activations Density 0.082%

    No Known Activations