© 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. 50917
    Prev
    Next
    INDEX
    Explanations

    word for

    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
     Verde
    -0.10
    esser
    -0.09
    éĺ®
    -0.09
    çŁ¿çī©
    -0.09
    åݳãģĹãģĦ
    -0.08
    ä¸¥æł¼æĮīçħ§
    -0.08
    _TYPED
    -0.07
    :min
    -0.07
    _SDK
    -0.07
     audit
    -0.07
    POSITIVE LOGITS
    ipes
    0.10
    åıijçĶŁäºĨ
    0.09
    acro
    0.09
    åħ¬è®¤çļĦ
    0.09
    åĻ¤
    0.09
    èºģ
    0.09
    èĬĬ
    0.09
    éŁŃ
    0.09
    ise
    0.09
    è´«åĽ°äººåı£
    0.08
    Activations Density 0.076%

    No Known Activations