© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9072
    Prev
    Next
    INDEX
    Explanations

    actions and functions

    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
    æıª
    -0.09
    ä¹ĭå¿ĥ
    -0.09
    pled
    -0.09
    semb
    -0.08
    ä¸Ģå¤ľ
    -0.08
    ANTE
    -0.08
    èĭĽ
    -0.08
     ÑħоÑĤ
    -0.08
    çĽ
    -0.08
    å¼Ħ
    -0.08
    POSITIVE LOGITS
     nhiá»ĩm
    0.14
    å±¥è¡Į
    0.14
    è¡Į使
    0.12
    å±¥èģĮ
    0.12
    使åij½
    0.11
    èģĮè´£
    0.11
    èģĮæĿĥ
    0.11
    åıijæĮ¥
    0.11
    èģĮèĥ½
    0.11
    èģĮåĬ¡
    0.11
    Activations Density 0.053%

    No Known Activations