© 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. 58255
    Prev
    Next
    INDEX
    Explanations

    comma followed by common conjunctions

    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
    ä½Ĩå¦Ĥæŀľ
    -0.10
    ãģķãģ¦
    -0.09
    çĦ¶èĢĮ
    -0.09
    æī¶
    -0.09
    è°İ
    -0.09
    ä¸Ķ
    -0.09
    oundation
    -0.09
    ensible
    -0.08
    ä½Ĩåį´
    -0.08
    Angel
    -0.08
    POSITIVE LOGITS
    åĩºäºİ
    0.10
    ize
    0.10
    виз
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    åijĺ
    0.09
    ä¹ĥèĩ³
    0.09
    å¤Ħäºİ
    0.09
    èĢĮéĿŀ
    0.09
    ãģ©ãģĵãĤį
    0.08
    æīĢè°ĵçļĦ
    0.08
    Activations Density 0.081%

    No Known Activations