© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8775
    Prev
    Next
    INDEX
    Explanations

    Microsoft Corporation copyright

    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
    emale
    -0.10
    èĢģ人家
    -0.10
    ires
    -0.09
    irm
    -0.09
    éĻ²
    -0.09
    ells
    -0.09
    åĦĨ
    -0.09
    iating
    -0.09
     Arabian
    -0.08
    ãĤīãģĦ
    -0.08
    POSITIVE LOGITS
    ally
    0.14
    nelle
    0.12
    ships
    0.11
    nal
    0.11
    nel
    0.10
    nels
    0.10
    azzi
    0.09
    ically
    0.09
    usty
    0.09
    allis
    0.09
    Activations Density 0.021%

    No Known Activations