© 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. 55150
    Prev
    Next
    INDEX
    Explanations

    backup and fallback plans

    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
    оде
    -0.09
    ALLE
    -0.09
    gang
    -0.09
    à¹Ģลย
    -0.09
    é¼ĵ
    -0.09
    lops
    -0.09
     gang
    -0.08
    rze
    -0.08
     Surprise
    -0.08
     اÙĦÙħست
    -0.08
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.22
    å¤ĩ
    0.17
    å¤ĩ份
    0.16
    åĤĻ
    0.16
     Backup
    0.16
     backup
    0.16
    .backup
    0.15
    ä¸ĩä¸Ģ
    0.15
     fallback
    0.14
    以éĺ²
    0.14
    Activations Density 0.090%

    No Known Activations