© 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. 19707
    Prev
    Next
    INDEX
    Explanations

    geared up

    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
    åĩ«
    -0.10
    姣
    -0.09
    æijĩ
    -0.08
    èĴĻ
    -0.08
    udd
    -0.08
    æIJĸ
    -0.08
    éĽĨè£ħç®±
    -0.08
    ãģĦãģ¾ãģĻ
    -0.08
    çĤ¯
    -0.08
    ists
    -0.08
    POSITIVE LOGITS
    èĦ¯
    0.10
    èĥ½æĬĬ
    0.09
    -up
    0.09
    æĹłæ¯Ķ
    0.09
    omatic
    0.09
    åįģ足
    0.09
     rid
    0.09
    zer
    0.09
    ster
    0.09
    åķĸ
    0.09
    Activations Density 0.012%

    No Known Activations