© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36700
    Prev
    Next
    INDEX
    Explanations

    teenage

    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
    èĪĮ
    -0.10
    ÄĻd
    -0.10
    stances
    -0.09
    -widgets
    -0.09
    大å¦Ī
    -0.09
    edImage
    -0.09
     standings
    -0.09
    itecture
    -0.09
    ìĤ¬íķŃ
    -0.09
    UME
    -0.09
    POSITIVE LOGITS
    hood
    0.12
    iates
    0.10
    inate
    0.09
    -old
    0.09
    ass
    0.09
    bra
    0.09
    avier
    0.09
    uates
    0.08
    eren
    0.08
    amma
    0.08
    Activations Density 0.007%

    No Known Activations