© 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. 34161
    Prev
    Next
    INDEX
    Explanations

    under- words

    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
     поÑģледние
    -0.10
    æĹĦ
    -0.10
    åħ»èĤ²
    -0.09
    åĭ¤
    -0.09
    çļĦæĦıè§ģ
    -0.09
    Prem
    -0.09
    黳
    -0.09
    utra
    -0.09
    ICLE
    -0.09
    éĢĢå½¹
    -0.09
    POSITIVE LOGITS
    izio
    0.09
    好å¤ļ
    0.09
    oad
    0.09
    å¤Ħåľ¨
    0.09
    åģļå¾Ĺ
    0.08
    tees
    0.08
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
    amento
    0.08
     unders
    0.08
    æķ´é¡¿
    0.08
    Activations Density 0.044%

    No Known Activations