© 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. 38299
    Prev
    Next
    INDEX
    Explanations

    below is a list

    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
    æľ¬èº«çļĦ
    -0.10
    .ta
    -0.10
    èĥ¸
    -0.10
    æľ¬èº«
    -0.09
    纵横
    -0.09
    æĹĥ
    -0.09
    s
    -0.09
    çĤ¹ç¼Ģ
    -0.09
    å¹²éĥ¨
    -0.09
    åıįè¿ĩæĿ¥
    -0.08
    POSITIVE LOGITS
    #{@
    0.10
    åį³æĺ¯
    0.09
    为大家
    0.09
    lé
    0.08
     GPLv
    0.08
    лоÑĤ
    0.08
    éĴĪ对
    0.08
    çĨŁæĤīçļĦ
    0.08
    æĥłåıĬ
    0.08
    ä¸Ģç³»åĪĹ
    0.08
    Activations Density 0.032%

    No Known Activations