© 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. 22007
    Prev
    Next
    INDEX
    Explanations

    state, condition, or belonging

    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
    å°Ķ
    -0.09
    主æĦı
    -0.09
    ific
    -0.09
    ç»Łæ²»
    -0.09
    æ´
    -0.09
    ieg
    -0.09
    çĶ¸
    -0.08
    SYS
    -0.08
    icult
    -0.08
    outing
    -0.08
    POSITIVE LOGITS
    ces
    0.10
    sson
    0.10
    èĢħçļĦ
    0.10
    aste
    0.09
     Cald
    0.09
    elines
    0.09
    åįģ足
    0.09
    akes
    0.08
    erton
    0.08
    è´£ç¼ĸ
    0.08
    Activations Density 0.099%

    No Known Activations