© 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. 7004
    Prev
    Next
    INDEX
    Explanations

    lead / leading

    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
    lds
    -0.09
    ting
    -0.08
    ead
    -0.08
    optic
    -0.08
    tal
    -0.08
    ç½ij讯
    -0.08
    å¿«ä¸ī
    -0.08
    /application
    -0.08
    æĭīä¸ģ
    -0.08
    åĿİ
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.10
    better
    0.10
    ños
    0.10
    erness
    0.10
    uten
    0.10
    nings
    0.09
    æ¶ĪåĮĸ
    0.09
    ings
    0.09
    ðŁı»
    0.09
    erv
    0.09
    Activations Density 0.040%

    No Known Activations