© 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. 53442
    Prev
    Next
    INDEX
    Explanations

    dreams, fantasy, imagining

    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
     ÑĤоÑĢ
    -0.10
    诱æĥij
    -0.09
    ä¸įæĺĵ
    -0.09
    æŬ
    -0.09
    arden
    -0.09
    æŁ¬åŁĶ寨
    -0.09
    ueue
    -0.08
    è°Į
    -0.08
    çļĦä¿¡ä»»
    -0.08
    æ¸ħæĻ°
    -0.08
    POSITIVE LOGITS
    .assertj
    0.10
    æľªæĪIJ
    0.09
    æĪijä¼ļ
    0.09
    IBLE
    0.09
     scenarios
    0.08
    åĽ½åº¦
    0.08
    置身
    0.08
    èĮĥæĸĩ
    0.08
     kostenlos
    0.08
     Ideal
    0.08
    Activations Density 0.027%

    No Known Activations