© 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. 10831
    Prev
    Next
    INDEX
    Explanations

    OpenID

    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
    reh
    -0.09
    ä¼ģä¸ļåıijå±ķ
    -0.09
    igham
    -0.09
    ç¬ij声
    -0.09
    å®ļåIJij
    -0.09
    çľĭä¸įè§ģ
    -0.08
    iasi
    -0.08
    æıĨ
    -0.08
    éĶĢ
    -0.08
    å¹ħ度
    -0.08
    POSITIVE LOGITS
    ision
    0.09
    Ñĩе
    0.09
    å¸ļ
    0.09
    eral
    0.09
    ful
    0.09
    usive
    0.09
    èĥĮä¸Ĭ
    0.09
    åľ¨åºĬä¸Ĭ
    0.08
    .dark
    0.08
    aison
    0.08
    Activations Density 0.003%

    No Known Activations