© 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. 11001
    Prev
    Next
    INDEX
    Explanations

    just [verb]

    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
    æĸ¹æīį
    -0.10
    欲
    -0.09
    åģ¶
    -0.09
    éģij
    -0.08
    Central
    -0.08
    为äºĨ
    -0.08
     ÑĥÑģл
    -0.08
    chor
    -0.08
    ÑģÑģ
    -0.08
    ç¿Ĵæħ£
    -0.08
    POSITIVE LOGITS
    çŀij
    0.10
    åijĹ
    0.10
    çŀĦåĩĨ
    0.10
    æ¯ĵ
    0.09
    éķ¿å¯¿
    0.09
    ERENCE
    0.09
    æĬ¬å¤´
    0.08
    å¤ļæķ°
    0.08
    ahr
    0.08
    èī¾
    0.08
    Activations Density 0.063%

    No Known Activations