© 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. 5152
    Prev
    Next
    INDEX
    Explanations

    particular profile

    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
    åħ½
    -0.08
    娱
    -0.08
    éĵ
    -0.08
    ð
    -0.08
    åł¡
    -0.08
    PLEMENT
    -0.07
    _fre
    -0.07
    /or
    -0.07
    åŃ½
    -0.07
    rossover
    -0.07
    POSITIVE LOGITS
    ÑĪка
    0.09
    زاÙĦ
    0.09
    apon
    0.09
    entication
    0.09
    åŁķ
    0.08
    à¸ģารà¹ģสà¸Ķà¸ĩ
    0.08
    ή
    0.08
    /photos
    0.08
    CREASE
    0.08
    entine
    0.08
    Activations Density 0.507%

    No Known Activations