© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20599
    Prev
    Next
    INDEX
    Explanations

    case study

    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
    orr
    -0.10
    èĭ
    -0.09
    æĸ°å¸¸æĢģ
    -0.09
    宾
    -0.09
    ä¹±
    -0.09
    èħ°
    -0.08
    è¿Īè¿Ľ
    -0.08
    ally
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    pu
    -0.08
    POSITIVE LOGITS
    æ¡Īä¾ĭ
    0.11
     case
    0.10
    èµı
    0.10
    åħ¸åŀĭæ¡Īä¾ĭ
    0.09
    case
    0.09
    å®ŀä¾ĭ
    0.09
    Forge
    0.09
    forge
    0.09
    ä¹ĭä½ľ
    0.09
    æĵį
    0.09
    Activations Density 0.089%

    No Known Activations