© 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. 52638
    Prev
    Next
    INDEX
    Explanations

    residential neighborhoods and streets

    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
    rosso
    -0.10
    åľºé¦Ĩ
    -0.09
    é¦Ĩ
    -0.09
    cade
    -0.09
     bord
    -0.09
    eworld
    -0.08
    ILES
    -0.08
    çŁ¿çī©è´¨
    -0.08
    Catalog
    -0.08
     ÑĢеÑģÑĤоÑĢ
    -0.08
    POSITIVE LOGITS
    å°ıåĮº
    0.12
    éĤ»å±ħ
    0.12
    åħ¥æĪ·
    0.11
    家éŨåı£
    0.11
    éĤ»éĩĮ
    0.11
    ä¸ĩæĪ·
    0.10
    neighbor
    0.10
    ä½ıå®ħ
    0.10
     neighborhoods
    0.10
     residential
    0.10
    Activations Density 0.269%

    No Known Activations