© 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. 5759
    Prev
    Next
    INDEX
    Explanations

    dates, names, and values

    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
    irts
    -0.10
    azard
    -0.10
    éĢł
    -0.09
    å°§
    -0.09
    çļĦåħ³éĶ®
    -0.09
    Ùĩد
    -0.09
    éħ¹
    -0.09
    iday
    -0.09
    ä¸įå°ı
    -0.09
     posed
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.14
    åħ·ä½ĵ
    0.12
    åĩºå¤Ħ
    0.11
     конкÑĢеÑĤ
    0.10
    å§ĵåIJį
    0.10
     estimate
    0.10
    è¿ijäºĽ
    0.09
    è¡ĮåĬ¨è®¡åĪĴ
    0.09
    ç¡®åĪĩ
    0.09
     date
    0.09
    Activations Density 0.163%

    No Known Activations