© 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. 19589
    Prev
    Next
    INDEX
    Explanations

    java annotations and imports

    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
    åĩī
    -0.10
    å¤Ħå¤Ħ
    -0.09
    çī¢åĽº
    -0.09
    Ñģоб
    -0.08
    éħ±
    -0.08
    åįģ足
    -0.08
    aura
    -0.08
    ova
    -0.08
    åĮı
    -0.08
    çݺ
    -0.08
    POSITIVE LOGITS
    好å¥ĩ
    0.09
    orea
    0.09
    BOR
    0.09
    _ABORT
    0.08
    ä¸į该
    0.08
    Mutable
    0.08
    åı¨
    0.08
    .arm
    0.08
    å¾Ĵ
    0.08
    飩
    0.08
    Activations Density 0.003%

    No Known Activations