© 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. 19186
    Prev
    Next
    INDEX
    Explanations

    raspberry pi

    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
    çĪ·
    -0.09
    é¹Ĺ
    -0.09
    urance
    -0.09
    ure
    -0.09
     Ñģвое
    -0.08
    åĪĨæĺİ
    -0.08
     stump
    -0.08
    imax
    -0.08
    otron
    -0.08
    uate
    -0.08
    POSITIVE LOGITS
    ting
    0.10
    etsk
    0.10
    /std
    0.10
    dale
    0.09
    åºĬä¸Ĭ
    0.09
    dar
    0.09
    èĭ´
    0.09
    bed
    0.09
    带头人
    0.09
    adies
    0.09
    Activations Density 0.007%

    No Known Activations