© 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. 48822
    Prev
    Next
    INDEX
    Explanations

    struggle to do something

    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
     dash
    -0.09
    åįģä¸ĩ
    -0.08
    aled
    -0.08
    ä¸įä½Ĩ
    -0.08
    è·ij
    -0.08
    tran
    -0.08
    åģıåģı
    -0.08
    æī¹åĪ¤
    -0.08
    race
    -0.08
    èĮħ
    -0.08
    POSITIVE LOGITS
    æĮ£æīİ
    0.13
     khÄĥn
    0.10
    éĩįéĩį
    0.10
    没åħ³ç³»
    0.10
    æĺ¯çľŁçļĦ
    0.09
    ingly
    0.09
    .cp
    0.09
    æī¾ä¸įåĪ°
    0.09
    ä»įå°Ĩ
    0.09
    ä¹ı
    0.09
    Activations Density 0.014%

    No Known Activations