© 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. 53427
    Prev
    Next
    INDEX
    Explanations

    suffix combinations like us, na, ml, ne, xc, rus

    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
    山寨
    -0.10
    adro
    -0.10
    çŀ»
    -0.10
    åIJ¬åĬĽ
    -0.10
    赡
    -0.10
    åĭ¤
    -0.10
    æŀķ
    -0.10
    æĮĩæĮ¥éĥ¨
    -0.09
     antic
    -0.09
    çIJħ
    -0.09
    POSITIVE LOGITS
    çĪ·
    0.08
     Sue
    0.08
    alls
    0.08
    å¿ĥ缮
    0.08
    rom
    0.08
    ows
    0.08
     Parkinson
    0.08
    åŁºå±Ĥ
    0.08
     po
    0.08
    волÑĮ
    0.08
    Activations Density 0.014%

    No Known Activations