© 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. 52581
    Prev
    Next
    INDEX
    Explanations

    full of

    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
    åIJIJ
    -0.11
    aring
    -0.09
    æĥħ人èĬĤ
    -0.09
    ically
    -0.09
    itant
    -0.08
    çĿĢçľ¼äºİ
    -0.08
    çĶ±æѤ
    -0.08
    elly
    -0.08
    çĮĽ
    -0.08
     ment
    -0.08
    POSITIVE LOGITS
    ness
    0.10
    ständ
    0.10
    -bodied
    0.10
    eren
    0.09
    moon
    0.09
     fled
    0.08
     dra
    0.08
     drafts
    0.08
    绪
    0.08
    _descr
    0.08
    Activations Density 0.035%

    No Known Activations