© 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. 2872
    Prev
    Next
    INDEX
    Explanations

    gathering or gatherings

    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
    aul
    -0.10
    lessly
    -0.09
    çĭŃçªĦ
    -0.09
    earch
    -0.08
    eus
    -0.08
    iro
    -0.08
    ç§ijæĬĢ大åѦ
    -0.08
    аÑĢÑĮ
    -0.08
    inium
    -0.08
    åĨįéĢł
    -0.08
    POSITIVE LOGITS
    ings
    0.14
    æĭ¢
    0.12
    CTL
    0.11
    æĶĺ
    0.10
    abouts
    0.10
    åı»
    0.10
    INGS
    0.10
    edException
    0.10
    æĩ¿
    0.09
    ungen
    0.09
    Activations Density 0.009%

    No Known Activations