© 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. 55938
    Prev
    Next
    INDEX
    Explanations

    something about

    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
    ä½łæĢİä¹Ī
    -0.10
    çĵ¢
    -0.10
    åĩŃä»Ģä¹Ī
    -0.10
    èij«
    -0.10
    åı¹
    -0.09
    pend
    -0.09
    åĪ¨
    -0.09
    adan
    -0.09
    åľ¨æĪijçļĦ
    -0.09
    å¡Ĭ
    -0.09
    POSITIVE LOGITS
    ëĶ°
    0.09
    èĢ³æľµ
    0.09
    iores
    0.09
    ÙĪرد
    0.08
    çļĦæĹ¥
    0.08
    ORN
    0.08
    æĿ¥çļĦ
    0.08
    (sig
    0.08
    éĤ¨
    0.08
    ockets
    0.08
    Activations Density 0.055%

    No Known Activations