© 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. 33779
    Prev
    Next
    INDEX
    Explanations

    sleek, slick, or streamlined adjectives

    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
    éĻIJãĤĬ
    -0.09
    endum
    -0.09
    aurus
    -0.08
     ÑįÑĤомÑĥ
    -0.08
    oya
    -0.08
    icont
    -0.08
    éĥijéĩį
    -0.08
    rift
    -0.08
    addin
    -0.08
    æĦŁåı¹
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    åĪ©
    0.10
    sters
    0.10
    ä¿IJ
    0.10
    ening
    0.09
    inc
    0.09
    spe
    0.09
    lok
    0.08
    ucker
    0.08
    _ELEMENTS
    0.08
    Activations Density 0.004%

    No Known Activations