© 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. 18101
    Prev
    Next
    INDEX
    Explanations

    reciting or recollection

    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
    éĻ²
    -0.10
    portun
    -0.09
    ãģ¹
    -0.09
    erial
    -0.08
    è¡Įäºĭ
    -0.08
    аÑħ
    -0.08
    å±İ
    -0.08
    itta
    -0.08
    adic
    -0.08
    ishly
    -0.08
    POSITIVE LOGITS
    æĨ¶
    0.10
    æµij
    0.10
    lox
    0.10
    esz
    0.09
    æľ¬é¢Ĩ
    0.09
    çĮ¬
    0.09
    è¶³å¤ŁçļĦ
    0.09
    åıijæĺİ
    0.08
    æĸĹå¿Ĺ
    0.08
    é¢Ĩä¼ļ
    0.08
    Activations Density 0.010%

    No Known Activations