© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    SEADE, ncer, ERMVD

    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
    æ¿Ģæĥħ
    -0.09
    á»ħn
    -0.09
    luet
    -0.09
    elin
    -0.08
    ertainment
    -0.08
    éĺħåİĨ
    -0.08
    à¤Ľ
    -0.08
     Ell
    -0.08
    IMA
    -0.08
    ÅĦ
    -0.08
    POSITIVE LOGITS
    æѦåĬŁ
    0.09
    æĢ»å±Ģ
    0.09
    å¾Ĺ罪
    0.09
    ç»Īç»ĵ
    0.09
    åıĮéĩį
    0.08
    绣é¢Ĩ
    0.08
    Vo
    0.08
    è¿ŀäºij
    0.08
    æĽ´é«ĺçļĦ
    0.08
    äºĭåIJİ
    0.08
    Activations Density 0.288%

    No Known Activations