© 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. 6547
    Prev
    Next
    INDEX
    Explanations

    frequently asked questions

    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
    置身
    -0.10
    upo
    -0.09
    寰
    -0.09
    ç½®
    -0.08
    éºŁ
    -0.08
    ACE
    -0.08
     Guy
    -0.08
    weed
    -0.08
    è°Ħ
    -0.08
    upa
    -0.08
    POSITIVE LOGITS
    FAQ
    0.14
    常è§ģ
    0.13
     FAQs
    0.13
     FAQ
    0.11
    faq
    0.11
     Frequently
    0.11
    客
    0.10
    çĸijéļ¾
    0.10
     fa
    0.10
    常è§ģçļĦ
    0.10
    Activations Density 0.063%

    No Known Activations