© 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. 23573
    Prev
    Next
    INDEX
    Explanations

    list or sentence endings

    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
    pond
    -0.08
    毳
    -0.08
    æ´¸
    -0.08
     fine
    -0.08
    åİķæīĢ
    -0.08
    åıijå±ķæ½ľåĬĽ
    -0.08
    ALSE
    -0.08
    ä¾Ľ
    -0.08
     "()
    -0.07
    æī§è¡ĮåĬĽ
    -0.07
    POSITIVE LOGITS
    æİĮæı¡
    0.09
    常è¯Ĩ
    0.09
    åħĪæĬĬ
    0.09
     вообÑīе
    0.08
    rite
    0.08
    _learn
    0.08
    äºĨ解
    0.08
    Tip
    0.08
    íĮģ
    0.08
    ä¸įä¿¡
    0.08
    Activations Density 0.104%

    No Known Activations