© 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. 11225
    Prev
    Next
    INDEX
    Explanations

    search for

    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
     cuckold
    -0.10
    ç¢Ľ
    -0.10
    .getCount
    -0.09
    icot
    -0.09
    çݯèĬĤ
    -0.09
    Implicit
    -0.09
    NullException
    -0.09
    าว
    -0.09
    LETTE
    -0.09
    iless
    -0.08
    POSITIVE LOGITS
    åħ³éĶ®è¯į
    0.13
    绵
    0.10
    åĨł
    0.10
     search
    0.10
    åĵį
    0.09
     keywords
    0.09
    çѵ
    0.09
    é¢ĺæĿIJ
    0.09
    éŁ¿
    0.09
    keywords
    0.09
    Activations Density 0.097%

    No Known Activations