© 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. 37553
    Prev
    Next
    INDEX
    Explanations

    (c)

    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
    ever
    -0.12
    åĵĩ
    -0.09
    æłĭ
    -0.09
    èĭ±çī¹
    -0.09
     tháºŃm
    -0.08
    è´Ń
    -0.08
    expo
    -0.08
    bies
    -0.08
    æĺĻ
    -0.08
    cols
    -0.08
    POSITIVE LOGITS
    æĪij个人
    0.10
    æĪij们认为
    0.10
    rys
    0.09
    éĿ
    0.09
    个人è§ĤçĤ¹
    0.09
    æľ¬èº«çļĦ
    0.08
    aines
    0.08
    æĮ¯åħ´
    0.08
    ãģ¹
    0.08
    spo
    0.08
    Activations Density 0.183%

    No Known Activations