© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and present participles

    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
    åı£æ°Ķ
    -0.10
    orge
    -0.10
    治好
    -0.09
    atum
    -0.09
    ä»İäºĭ
    -0.09
    ackers
    -0.09
     kitty
    -0.09
    严å¯Ĩ
    -0.09
    DataStream
    -0.09
    оÑĩка
    -0.08
    POSITIVE LOGITS
    åĪ°å¤Ħ
    0.09
    еÑĢÑĤ
    0.09
    ROUT
    0.09
    å°±åºĶ该
    0.08
    å¢ŀ
    0.08
    表çĻ½
    0.08
     Magn
    0.08
    æľĪä¸ĭ
    0.08
    èĸ°
    0.08
    åħļç»ĦæĪIJåijĺ
    0.08
    Activations Density 0.076%

    No Known Activations