© 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. 63228
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    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
    åħŃåIJĪ
    -0.10
    нÑıÑĤÑĮ
    -0.09
    æĶ¾æĺł
    -0.09
     ÑħозÑı
    -0.09
    åij¨ä¸Ģ
    -0.08
    åĬ©
    -0.08
    åĮķ
    -0.08
    Êĭ
    -0.08
    éĴ²
    -0.08
     hint
    -0.08
    POSITIVE LOGITS
    è¹²
    0.10
    nod
    0.09
    åı«æĪij
    0.08
    以èī²
    0.08
    ilst
    0.08
    èĤ²äºº
    0.08
    åıªçŁ¥éģĵ
    0.08
     sac
    0.08
     Sac
    0.08
    çŃĴ
    0.08
    Activations Density 0.240%

    No Known Activations