© 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. 33086
    Prev
    Next
    INDEX
    Explanations

    arrests, closures, appointments

    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
    burg
    -0.10
    ä¾Ŀæ³ķ追究
    -0.09
    åĥ
    -0.08
    ivot
    -0.08
    ä½İä¸ĭ
    -0.08
    berger
    -0.08
    å¿įåıĹ
    -0.08
    /helper
    -0.08
    第
    -0.08
    åĿŀ
    -0.08
    POSITIVE LOGITS
    Occurred
    0.12
    åıijçĶŁåľ¨
    0.12
     erfol
    0.11
    achi
    0.11
    é¢Ħè¨Ģ
    0.11
    Made
    0.10
    çļĦåıijçĶŁ
    0.10
     done
    0.10
    åıijçĶŁçļĦ
    0.09
    ç¾½
    0.09
    Activations Density 0.353%

    No Known Activations