© 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. 34601
    Prev
    Next
    INDEX
    Explanations

    full of [something]

    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
    ä¸Ģå¹ķ
    -0.13
    ched
    -0.10
    ä»»ä½ķæŶåĢĻ
    -0.09
    æĹģ
    -0.08
    rog
    -0.08
    ä¸ĢåĪ»
    -0.08
    åĪ©çĶ¨çİĩ
    -0.08
    åįģéĩĮ
    -0.08
    perature
    -0.08
    ese
    -0.08
    POSITIVE LOGITS
    iated
    0.10
    çģĮ
    0.10
    è¹Ī
    0.10
    èıĬèĬ±
    0.09
    CUS
    0.09
    çĸĻ
    0.09
    èĨº
    0.09
    èĢĮåıĪ
    0.09
    redo
    0.08
    gado
    0.08
    Activations Density 0.007%

    No Known Activations