© 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. 23773
    Prev
    Next
    INDEX
    Explanations

    causal or temporal conjunctions

    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
     âĢº
    -0.09
     доÑģÑĤиж
    -0.09
    ä¾
    -0.08
    认è¯ĨåĪ°
    -0.08
    赶
    -0.08
    认è¯Ĩ
    -0.08
    ube
    -0.07
    çĶĺ
    -0.07
    _PIXEL
    -0.07
     Foot
    -0.07
    POSITIVE LOGITS
    å³Ń
    0.12
    æŀķ头
    0.09
    å©¿
    0.09
    å¹Į
    0.09
    ä½ľåĵģåĨħ容
    0.09
    æģģ
    0.09
    åĪ°æŶåĢĻ
    0.09
    adge
    0.09
    å®ļæľŁ
    0.09
    çĢijå¸ĥ
    0.09
    Activations Density 0.038%

    No Known Activations