© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50869
    Prev
    Next
    INDEX
    Explanations

    for good / better / sure / real

    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
    åħ¨æµģç¨ĭ
    -0.10
    éĵ§
    -0.09
    VEL
    -0.09
    ç«ĭæ¡Ī
    -0.09
    åĪ©çī©
    -0.09
    axter
    -0.09
    aked
    -0.08
    hung
    -0.08
    anged
    -0.08
    åIJĥå®Į
    -0.08
    POSITIVE LOGITS
    èĶĹ
    0.09
    æIJº
    0.09
    atura
    0.08
    人å¿ĥ
    0.08
     prere
    0.08
    ÑĩÑĥв
    0.08
    ä¸Ī
    0.08
    æ°¸ä¹ħ
    0.08
    ries
    0.08
    ely
    0.08
    Activations Density 0.025%

    No Known Activations