© 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. 4680
    Prev
    Next
    INDEX
    Explanations

    "word" followed by quotation marks or specific words

    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
    è¯Ŀ说
    -0.09
    æŀ§
    -0.09
    .codes
    -0.09
    éķ¿éķ¿
    -0.09
    ÑĥÑĩа
    -0.08
    ArrayOf
    -0.08
    çıįçıł
    -0.08
    ListOf
    -0.08
    èĶ·
    -0.08
    è±Į
    -0.08
    POSITIVE LOGITS
    迹
    0.10
    opper
    0.09
    åħ¸
    0.09
    ä»ŀ
    0.09
    ä»Ģä¹Īäºĭ
    0.09
    ìĹ´
    0.08
    tas
    0.08
    åİĭè¿«
    0.08
    imate
    0.08
    åĩłæ¬¡
    0.08
    Activations Density 0.042%

    No Known Activations