© 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. 51573
    Prev
    Next
    INDEX
    Explanations

    roads and street names

    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
    TING
    -0.12
    mó
    -0.09
    è°İ
    -0.09
    iting
    -0.09
    AGMA
    -0.09
    çļ¿
    -0.09
    itarian
    -0.08
    çıŃåŃIJ
    -0.08
    ãģĭãĤĤ
    -0.08
    retval
    -0.08
    POSITIVE LOGITS
    side
    0.11
    ìį¨
    0.11
    stead
    0.11
    vertiser
    0.11
    vertising
    0.10
    vertisement
    0.10
    sworth
    0.10
    ways
    0.10
    omain
    0.10
    mary
    0.10
    Activations Density 0.023%

    No Known Activations