© 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. 35349
    Prev
    Next
    INDEX
    Explanations

    did not know

    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
    ä¸į容æĺĵ
    -0.11
    è¦ģåģļ好
    -0.09
     вполне
    -0.09
    çħ¨
    -0.09
    ainen
    -0.09
    ä¸įå¿ĺ
    -0.09
    [at
    -0.09
    anes
    -0.09
    æĪijä¸į
    -0.09
    heel
    -0.08
    POSITIVE LOGITS
     until
    0.10
    缴åĪ°
    0.10
     пока
    0.10
    è¿ĺ以为
    0.09
    until
    0.09
    imps
    0.09
    ä¸ĭæīĭ
    0.09
    åħ¶å®ŀå°±æĺ¯
    0.08
     lắm
    0.08
     eigentlich
    0.08
    Activations Density 0.049%

    No Known Activations