© 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. 39602
    Prev
    Next
    INDEX
    Explanations

    cut out

    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
    remen
    -0.09
    olph
    -0.09
    ä¸įä¸Ĭ
    -0.08
     ext
    -0.08
    rolls
    -0.08
    åij½
    -0.08
    ening
    -0.08
     Gew
    -0.08
    ash
    -0.08
    æŁı
    -0.08
    POSITIVE LOGITS
    çĮľ
    0.10
    æ¿ij
    0.09
    è¹´
    0.09
    åĩ«
    0.09
    大æĪ·
    0.09
    å°ī
    0.09
    AVA
    0.09
    èĻı
    0.08
    ä¸Ńå¼ı
    0.08
    æ¡IJ
    0.08
    Activations Density 0.006%

    No Known Activations