© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10259
    Prev
    Next
    INDEX
    Explanations

    under a name or title

    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
    builtin
    -0.09
    ateg
    -0.09
    æıª
    -0.09
    Usage
    -0.09
    èŁ¹
    -0.08
     ded
    -0.08
    è¿«
    -0.08
     Ernst
    -0.08
     unspecified
    -0.08
     Usage
    -0.08
    POSITIVE LOGITS
    è¿Ļ个åIJįåŃĹ
    0.12
    åIJįåı«
    0.10
    åIJį为
    0.10
    å§
    0.09
    çĴİ
    0.09
    车çīĮ
    0.09
    æĹĹä¸ĭ
    0.08
    åįĥä¸ĩ
    0.08
     under
    0.08
    个ä½ĵ
    0.08
    Activations Density 0.111%

    No Known Activations