© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36113
    Prev
    Next
    INDEX
    Explanations

    well-nigh, enough, requisite

    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
    ên
    -0.09
    .bd
    -0.08
     иÑģпол
    -0.08
    avar
    -0.08
     Warfare
    -0.08
    etch
    -0.08
    ames
    -0.07
    ÃŃt
    -0.07
    haar
    -0.07
    .fd
    -0.07
    POSITIVE LOGITS
    è¿ĻèĪ¬
    0.09
    INGS
    0.09
    ings
    0.09
    edly
    0.09
    ãģªãĤĭ
    0.09
    æĪij以为
    0.09
    -fi
    0.08
    uhe
    0.08
    åĬłä»¥
    0.08
    åĩ¤åĩ°
    0.08
    Activations Density 0.401%

    No Known Activations