© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56652
    Prev
    Next
    INDEX
    Explanations

    public houses and similar places

    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
    ãģ°
    -0.09
    表æĢģ
    -0.09
    çħİ
    -0.09
    éľĦ
    -0.09
    迦
    -0.09
    oft
    -0.09
    åIJ¸åıĸ
    -0.09
    çijĻ
    -0.09
    ean
    -0.08
    ç¹ģ
    -0.08
    POSITIVE LOGITS
    éĩĮçļĦ
    0.10
    è¡Ĺ
    0.09
    佬
    0.09
    keeper
    0.09
    yard
    0.08
    thood
    0.08
    keepers
    0.08
    (crate
    0.08
    gers
    0.08
     PED
    0.08
    Activations Density 0.012%

    No Known Activations