© 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. 37829
    Prev
    Next
    INDEX
    Explanations

    a part of

    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
    idy
    -0.09
    驹
    -0.09
    ç©¿æĪ´
    -0.08
    fo
    -0.08
    clud
    -0.08
    åij¼
    -0.08
     Mystic
    -0.08
     лиÑĤеÑĢаÑĤÑĥÑĢ
    -0.08
    ao
    -0.08
    ifter
    -0.08
    POSITIVE LOGITS
    çĥ¨
    0.10
    ãģŀ
    0.09
    èĬ«
    0.09
    å¢ħ
    0.09
    ä¸įä¸Ĭ
    0.09
    èĩ´åĬĽ
    0.08
    åĽĽåij¨
    0.08
    æĩĴå¾Ĺ
    0.08
    erial
    0.08
    éķĬ
    0.08
    Activations Density 0.005%

    No Known Activations