© 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. 30885
    Prev
    Next
    INDEX
    Explanations

    release under license or dates

    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
    /from
    -0.10
    ewe
    -0.09
    åįģ足
    -0.09
    iliar
    -0.09
    à¹Į
    -0.09
    ities
    -0.08
    æĬĺ磨
    -0.08
    åįĩèµ·
    -0.08
    resses
    -0.08
    åĦ¿
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģ
    0.10
    oretical
    0.10
    äºĨèĩªå·±çļĦ
    0.09
    ively
    0.09
    asm
    0.09
    ables
    0.09
    aron
    0.09
    ÙĦÙĬÙĨ
    0.09
    ARP
    0.09
    Ñĭ
    0.09
    Activations Density 0.061%

    No Known Activations