© 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. 53870
    Prev
    Next
    INDEX
    Explanations

    furniture and chairs

    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
    assy
    -0.10
    èĨı
    -0.10
    ickerView
    -0.10
    è´§çī©
    -0.10
    çħ§äº®
    -0.09
    ä¸Ģéĥ¨
    -0.09
    _MISS
    -0.09
    èĽ¾
    -0.09
    ANNEL
    -0.09
     McCart
    -0.09
    POSITIVE LOGITS
    æ¤ħåŃIJ
    0.15
    æ¤ħ
    0.14
     chairs
    0.13
    åĿIJçĿĢ
    0.12
     chair
    0.11
     Chairs
    0.11
    åĩ³
    0.10
    åĺİ
    0.10
     resh
    0.10
     stool
    0.09
    Activations Density 0.053%

    No Known Activations