© 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. 26909
    Prev
    Next
    INDEX
    Explanations

    a state of existence or possession

    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
    说åĩºæĿ¥
    -0.11
    inous
    -0.10
     rele
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    ãģĦãģĭ
    -0.09
    åĽ½éĻħåIJĪä½ľ
    -0.09
    èĢĮæĺ¯
    -0.08
    åĿĬ
    -0.08
    æijĩ头
    -0.08
    illi
    -0.08
    POSITIVE LOGITS
    å½ĵçĦ¶
    0.12
    ä¹ŁåĽłæѤ
    0.12
     же
    0.11
     ë¬¼ë¡ł
    0.10
     ÑĤакже
    0.10
     конеÑĩно
    0.10
     meanwhile
    0.09
    çķ¶çĦ¶
    0.09
     also
    0.09
    åĽłæѤ
    0.09
    Activations Density 0.317%

    No Known Activations