© 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. 36381
    Prev
    Next
    INDEX
    Explanations

    respective [noun]

    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
    æĻ°
    -0.09
    Specifications
    -0.09
    6
    -0.08
    åŀĭä¼ģä¸ļ
    -0.08
    7
    -0.08
    5
    -0.08
    hoot
    -0.08
    ä¹ĭ举
    -0.08
    3
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    ively
    0.15
    vely
    0.10
    otch
    0.10
    hood
    0.10
    atten
    0.10
    /current
    0.09
    æŶéĹ´åĨħ
    0.09
     Brewing
    0.09
    haust
    0.09
    ủ
    0.09
    Activations Density 0.014%

    No Known Activations