© 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. 48410
    Prev
    Next
    INDEX
    Explanations

    household and family structures

    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
    è¿ĺ羣
    -0.09
    èĢģçĻ¾å§ĵ
    -0.08
    大æĪ·
    -0.08
    åħħå®ŀ
    -0.07
    oll
    -0.07
    è¿ĽåĮĸ
    -0.07
    çİ©æ³ķ
    -0.07
     Quiet
    -0.07
    ç¥ł
    -0.07
    ä¿Ŀåħ»
    -0.07
    POSITIVE LOGITS
    伸æīĭ
    0.11
    żu
    0.10
    .mods
    0.10
    åĿļå®ļ
    0.10
    çĤ¼
    0.09
    çħī
    0.09
    uale
    0.09
    派驻
    0.09
    è¡·
    0.09
    åĪĨ解
    0.09
    Activations Density 0.026%

    No Known Activations