© 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. 6739
    Prev
    Next
    INDEX
    Explanations

    adding that

    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
    æģ©
    -0.10
    atra
    -0.09
    轩è¾ķ
    -0.09
    лим
    -0.09
    _lit
    -0.08
    æ¦Ħ
    -0.08
    âĿ®
    -0.08
    íijľ
    -0.08
     Fang
    -0.08
    ibil
    -0.08
    POSITIVE LOGITS
    åĨ°åĨ·
    0.10
    nts
    0.09
    iente
    0.09
    çĤ¹å¤ļ
    0.08
    ient
    0.08
    ctor
    0.08
    TC
    0.08
    å¼Ģåĩº
    0.08
    ä¸įå¿ĺ
    0.08
    ashes
    0.08
    Activations Density 0.016%

    No Known Activations