© 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. 53365
    Prev
    Next
    INDEX
    Explanations

    which or what to decide

    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
    éĻįä½İäºĨ
    -0.10
    éĢŁåº¦å¿«
    -0.10
    éģĩåĪ°äºĨ
    -0.10
     pret
    -0.09
    OSC
    -0.09
    åĩıå°ijäºĨ
    -0.09
    vince
    -0.09
    解åĨ³äºĨ
    -0.09
    eson
    -0.08
    é¢Ħ
    -0.08
    POSITIVE LOGITS
     to
    0.17
    ToRemove
    0.11
    è¦ģ好好
    0.11
    ToDelete
    0.10
    è¦ģåľ¨
    0.10
    è¦ģåİ»
    0.10
    è¦ģåĿļæĮģ
    0.10
    è¦ģ
    0.10
    å°±æĺ¯è¦ģ
    0.10
    è¦ģçľĭ
    0.10
    Activations Density 0.076%

    No Known Activations