© 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. 35873
    Prev
    Next
    INDEX
    Explanations

    housing related terms

    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
    碼
    -0.10
    éĿ¢çĽ®
    -0.10
    stakes
    -0.10
    .localization
    -0.09
    dish
    -0.09
    nels
    -0.09
    isters
    -0.09
    å¤ļæĸ¹
    -0.09
     Martial
    -0.09
    ãģ¨ãĤĬ
    -0.09
    POSITIVE LOGITS
    mates
    0.12
    chool
    0.10
    lust
    0.09
    mate
    0.09
    annon
    0.09
    ç§ijåѦåıijå±ķ
    0.09
    ĺ
    0.09
    cent
    0.08
    less
    0.08
    ancock
    0.08
    Activations Density 0.015%

    No Known Activations