© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    assortment and assault

    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
    beros
    -0.09
    isser
    -0.09
    yon
    -0.09
    ستاÙĨ
    -0.08
    åįģ足
    -0.08
     sheer
    -0.08
    andal
    -0.08
    æĸ¯é¡¿
    -0.08
     horn
    -0.08
    erea
    -0.08
    POSITIVE LOGITS
    ments
    0.13
    ment
    0.13
    ively
    0.12
    itude
    0.12
    é½IJåħ¨
    0.11
    ingly
    0.10
     sÃłng
    0.10
    oggle
    0.09
    ellaneous
    0.09
    illery
    0.09
    Activations Density 0.004%

    No Known Activations