© 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. 35793
    Prev
    Next
    INDEX
    Explanations

    would expect/need/be

    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
    kop
    -0.09
    nee
    -0.09
    åĽ¹
    -0.09
     ÑĢеÑĪа
    -0.09
    isms
    -0.09
    ä»Ķ
    -0.09
    ä¸ĥæĺŁ
    -0.09
    ledon
    -0.09
    缮çļĦåľ°
    -0.09
    led
    -0.09
    POSITIVE LOGITS
     Coc
    0.09
    orp
    0.09
    æĦıæĥ³ä¸įåĪ°
    0.09
    åĪ«
    0.09
    etail
    0.09
    know
    0.08
    åIJ¬è§ģ
    0.08
    çŁ¥éģĵ
    0.08
    没æĥ³åĪ°
    0.08
    erial
    0.08
    Activations Density 0.014%

    No Known Activations