© 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. 18617
    Prev
    Next
    INDEX
    Explanations

    consists or lies

    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
    æ¡IJ
    -0.09
    /fixtures
    -0.09
    æľªæĪIJ
    -0.09
    inc
    -0.09
    hea
    -0.09
     Inc
    -0.09
    è¶Ĭè¿ĩ
    -0.09
    tober
    -0.08
    vier
    -0.08
    ä¾ĽéĶĢ
    -0.08
    POSITIVE LOGITS
    åľ¨äºİ
    0.11
    alone
    0.11
    å°±åľ¨äºİ
    0.11
    lay
    0.10
     Westminster
    0.10
    èıģ
    0.10
    åĬŁå¾·
    0.10
    rame
    0.10
    仪表
    0.09
    åºĸ
    0.09
    Activations Density 0.019%

    No Known Activations