© 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. 26819
    Prev
    Next
    INDEX
    Explanations

    number of bedrooms and bathrooms

    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
    åįļ
    -0.10
    åĨľè´¸
    -0.09
    åIJĮç±»
    -0.09
    å¯Ħæīĺ
    -0.09
    ä¸Ģè¶Ł
    -0.09
    绩æķĪ
    -0.08
    åĴķ
    -0.08
    alone
    -0.08
    ollo
    -0.08
    oise
    -0.08
    POSITIVE LOGITS
    æĬķåħ¥åĪ°
    0.09
    沿çĿĢ
    0.09
    沿
    0.09
     Ow
    0.08
    (assert
    0.08
    沿éĢĶ
    0.08
    ÑĤÑĥÑĢ
    0.08
    æĵ¦
    0.08
    é«ĺçļĦ
    0.08
    å¯ĵæĦı
    0.08
    Activations Density 0.009%

    No Known Activations