© 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. 32702
    Prev
    Next
    INDEX
    Explanations

    copyright notices with associated names

    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
    nt
    -0.10
    ä¹İ
    -0.09
    chia
    -0.09
    ny
    -0.08
    íĤ¬
    -0.08
     Slug
    -0.08
    åŁ
    -0.08
    ument
    -0.08
     Verde
    -0.08
    带åĽŀ
    -0.08
    POSITIVE LOGITS
    หม
    0.11
    æķ£æĸĩ
    0.10
    -placeholder
    0.09
    asz
    0.09
    é«ĺå³°
    0.09
    arious
    0.09
    è¹ĩ
    0.09
    ç¼Ģ
    0.09
    .ASCII
    0.09
    DOG
    0.08
    Activations Density 0.053%

    No Known Activations