© 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. 56891
    Prev
    Next
    INDEX
    Explanations

    inspired by

    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
    erde
    -0.10
    夺
    -0.09
    符åIJĪ
    -0.09
    èĦĸ
    -0.09
    ere
    -0.09
    cho
    -0.09
    anel
    -0.09
    utron
    -0.09
    è°ĵ
    -0.09
    erable
    -0.09
    POSITIVE LOGITS
    å®ŀéĻħæĥħåĨµ
    0.10
    åį³å°ĨåĪ°æĿ¥
    0.10
    å·²ä¹ħ
    0.10
    çİ°å®ŀçĶŁæ´»
    0.09
    身边çļĦ
    0.09
    åij¨åĽ´çļĦ
    0.08
    æľĢè¿ij
    0.08
    èĤ¡
    0.08
    åħĪåīį
    0.08
    为æĤ¨
    0.08
    Activations Density 0.042%

    No Known Activations