© 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. 52079
    Prev
    Next
    INDEX
    Explanations

    particular [file/folder/emphasis/state/compounds]

    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
    جب
    -0.09
    é£ŀæī¬
    -0.09
    elen
    -0.09
    ODO
    -0.08
    èİ«è¿ĩäºİ
    -0.08
    iji
    -0.08
    ela
    -0.08
    pare
    -0.08
    adal
    -0.08
    _VO
    -0.08
    POSITIVE LOGITS
    ity
    0.14
    ities
    0.12
    ially
    0.12
    istic
    0.11
    ized
    0.10
    iveness
    0.10
    ple
    0.10
    zelf
    0.09
    ÙħصÙĦØŃØ©
    0.09
    èĬĿ
    0.09
    Activations Density 0.047%

    No Known Activations