© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8283
    Prev
    Next
    INDEX
    Explanations

    District Court

    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
    æ¾İæ¹ĥæĸ°éĹ»
    -0.09
    nty
    -0.09
    å¼Ĥåij³
    -0.09
    erring
    -0.08
    åŃ©
    -0.08
    åIJ¯åıij
    -0.08
    å¹ħ度
    -0.08
    itech
    -0.08
     implicit
    -0.08
    ä¸ĸä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æĸ¹å¼ıè¿Ľè¡Į
    0.10
    ä¸įèĥ½åĨį
    0.10
    orado
    0.10
    éĶ¦ç»£
    0.09
    alent
    0.09
    客
    0.09
     hè
    0.09
    /dom
    0.09
    å½¼å¾Ĺ
    0.09
    PCM
    0.09
    Activations Density 0.151%

    No Known Activations