© 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. 18059
    Prev
    Next
    INDEX
    Explanations

    past tense of to be + past participle

    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¤ļåįĬ
    -0.10
    è¦ģä¸įçĦ¶
    -0.09
     ÐĴам
    -0.09
    çŃī级
    -0.09
    椹
    -0.08
    çĶŁæĢķ
    -0.08
    hev
    -0.08
    èħĬ
    -0.08
    _increment
    -0.08
    对åħ¶è¿Ľè¡Į
    -0.08
    POSITIVE LOGITS
    æīĵéĢłæĪIJ
    0.11
    å¾Ĺèµ·
    0.10
    æ´¾
    0.09
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.09
    åĪĹ为
    0.09
    åıįå¤į
    0.09
    urge
    0.09
    å¼ķåħ¥
    0.09
     Tut
    0.09
    ç§ijåѦåıijå±ķ
    0.09
    Activations Density 0.211%

    No Known Activations