© 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. 7337
    Prev
    Next
    INDEX
    Explanations

    playoff elimination scenarios

    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
    ities
    -0.12
    端æŃ£
    -0.10
    èĬ±èįī
    -0.10
    OfClass
    -0.10
    éķ¿è¿ľ
    -0.09
    -eye
    -0.09
    ties
    -0.09
    ä¸ĢåĪĢ
    -0.08
    è¾ķ
    -0.08
    dds
    -0.08
    POSITIVE LOGITS
    æݸ
    0.10
    æľŁéĹ´
    0.10
    اÙĥ
    0.10
    IFY
    0.09
    -ready
    0.09
    uant
    0.09
    swith
    0.08
    ä¼IJ
    0.08
    æ±Łåİ¿
    0.08
    -bound
    0.08
    Activations Density 0.011%

    No Known Activations