© 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. 53302
    Prev
    Next
    INDEX
    Explanations

    verbs ending in ing

    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
    å½»
    -0.10
    å±ıéļľ
    -0.10
    oftware
    -0.09
    еÑĢÑĮ
    -0.09
    æī¿æİ¥
    -0.09
    çļĦå±ĢéĿ¢
    -0.08
    士
    -0.08
    оÑĩек
    -0.08
    oyer
    -0.08
    çħ
    -0.08
    POSITIVE LOGITS
    为äºĨ让
    0.08
    ä½İè°ĥ
    0.08
    äºĨåįĬ天
    0.08
    æķij人
    0.08
     Kö
    0.08
    stown
    0.08
    åIJĮå¹´
    0.08
    roud
    0.08
    _LOOK
    0.08
    myp
    0.08
    Activations Density 0.132%

    No Known Activations