© 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. 1316
    Prev
    Next
    INDEX
    Explanations

    UNESCO, agency, professional, Directive

    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
    çī¢
    -0.10
    çĵ£
    -0.09
    积åĪĨ
    -0.09
    é£İè²Į
    -0.09
    æĢģ度
    -0.09
    çĤī
    -0.09
    çIJ¦
    -0.09
    ted
    -0.09
    æŀ«
    -0.09
    å¤ļä½ĻçļĦ
    -0.09
    POSITIVE LOGITS
    èĥľ
    0.10
    æĻºåĬĽ
    0.09
    olia
    0.09
    yna
    0.08
    èĤļ
    0.08
     Mandela
    0.08
    íij¸
    0.08
     Bout
    0.08
     McCabe
    0.08
     mind
    0.08
    Activations Density 0.012%

    No Known Activations