© 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. 11971
    Prev
    Next
    INDEX
    Explanations

    knowing that or how

    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
    /is
    -0.10
    éłĵ
    -0.09
    éĽķ
    -0.08
    åħĭæĸ¯
    -0.08
    ooks
    -0.08
    ed
    -0.08
    al
    -0.08
    ÑĮ
    -0.07
    é¡¿
    -0.07
    eed
    -0.07
    POSITIVE LOGITS
    èĥ½åĬĽåĴĮ
    0.11
     paran
    0.10
    åįĩèµ·
    0.10
    rones
    0.10
    çĤ¹çĤ¹å¤´
    0.10
    æģ°å½ĵ
    0.09
     знаÑİ
    0.09
    éķ£
    0.09
    _ability
    0.09
    nom
    0.09
    Activations Density 0.013%

    No Known Activations