© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6724
    Prev
    Next
    INDEX
    Explanations

    real estate transaction phases

    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
    æĴ
    -0.10
    å¹´éĻIJ
    -0.09
    æĭ£
    -0.09
    çķª
    -0.09
    åijĨ
    -0.09
    umont
    -0.08
    çł´
    -0.08
    æĴĴ
    -0.08
     McKin
    -0.08
    å²ģæľĪ
    -0.08
    POSITIVE LOGITS
    åŁĿ
    0.10
    ç»¿åľ°
    0.10
     hẹn
    0.10
    å®īåħ¨æĦŁ
    0.09
    ç»ı纪人
    0.09
    客æĪ·éľĢæ±Ĥ
    0.09
    æĸ°æĪ¿
    0.09
     Downing
    0.09
    汩
    0.09
    å¾ĭå¸Ī
    0.09
    Activations Density 0.095%

    No Known Activations