© 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. 2673
    Prev
    Next
    INDEX
    Explanations

    time to develop or prepare

    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
    缸è§ģ
    -0.09
    UNK
    -0.09
    izon
    -0.08
    .moveToFirst
    -0.08
    azer
    -0.08
    even
    -0.08
    quan
    -0.08
    quia
    -0.08
    _dispatcher
    -0.08
    éĤĢ
    -0.08
    POSITIVE LOGITS
    积èĵĦ
    0.13
    赶ä¸Ĭ
    0.12
    åħħåĪĨ
    0.12
    æ¶ĪåĮĸ
    0.11
    çĨŁæĤī
    0.11
    秣
    0.10
    追赶
    0.10
    èĵĦ
    0.10
    ETS
    0.10
     catch
    0.10
    Activations Density 0.052%

    No Known Activations