© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16817
    Prev
    Next
    INDEX
    Explanations

    effective date

    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
    Negative Logits
    foil
    -0.09
    æĥħ绪
    -0.09
    hoc
    -0.09
     pied
    -0.08
     Hob
    -0.08
    quam
    -0.08
    æĸ°é²ľ
    -0.08
    duc
    -0.08
    oid
    -0.08
    ä¸įä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä¸įä¹ħ
    0.10
    itas
    0.10
    æľŁåĨħ
    0.09
    驺
    0.09
    ivr
    0.09
    cci
    0.08
     Wid
    0.08
    ãģ¾ãģ¾
    0.08
     Colin
    0.08
    ä¸į代表
    0.08
    Activations Density 0.021%

    No Known Activations