© 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. 30504
    Prev
    Next
    INDEX
    Explanations

    intelligence and IQ

    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
    ide
    -0.08
    ings
    -0.08
    itsu
    -0.08
    峤
    -0.08
    Fonts
    -0.08
    ipa
    -0.08
     Palin
    -0.08
    NT
    -0.08
    esa
    -0.08
    hs
    -0.08
    POSITIVE LOGITS
    ç¾ļ
    0.10
    çĥĿ
    0.10
    èł¢
    0.10
     возможно
    0.09
    CRY
    0.09
    伸åĩº
    0.09
    å³Ļ
    0.09
    é¢Ľ
    0.09
    æĤ¬
    0.09
    è¶Ĭé«ĺ
    0.09
    Activations Density 0.014%

    No Known Activations