© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    Dodge Chrysler Honduras

    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
    é»İ
    -0.11
    åħ¶æīĢ
    -0.10
    ennie
    -0.10
    вез
    -0.10
     Eyl
    -0.09
    orthand
    -0.09
     phẩm
    -0.09
    çļ¿
    -0.09
    и
    -0.08
    ние
    -0.08
    POSITIVE LOGITS
    erate
    0.10
    è¹Ī
    0.09
    วà¸ģ
    0.08
    angelo
    0.08
    à¹Į
    0.08
    åIJĥå®Į
    0.08
     Casino
    0.08
    èĢĹ
    0.08
    оÑĩно
    0.08
     Bet
    0.08
    Activations Density 0.006%

    No Known Activations