© 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. 34004
    Prev
    Next
    INDEX
    Explanations

    environmental quality and implications

    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
    æĬµæĮ¡
    -0.10
    عÙħ
    -0.10
    åĬŀå®ŀäºĭ
    -0.09
    leon
    -0.09
    otr
    -0.09
    åĨķ
    -0.08
    rift
    -0.08
    wayne
    -0.08
    åĭī强
    -0.08
    åķĨéĩı
    -0.07
    POSITIVE LOGITS
    åĢ¬
    0.11
     Orr
    0.11
    ä¹į
    0.10
    åĽ¢å§Ķ
    0.09
    ä¸Ģä¼ļ
    0.09
    -messages
    0.09
    INK
    0.09
    Scaler
    0.09
    ink
    0.09
    çī¢è®°
    0.09
    Activations Density 0.026%

    No Known Activations