© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    past and history

    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
    .notice
    -0.08
    åĿĤ
    -0.08
    aturas
    -0.08
    èĪŁ
    -0.08
    atura
    -0.08
     ÑģобиÑĢа
    -0.08
    оÑĩно
    -0.07
    iero
    -0.07
    罩
    -0.07
    abox
    -0.07
    POSITIVE LOGITS
    è¿ĩåİ»
    0.22
     past
    0.21
    è¿ĩåİ»çļĦ
    0.21
    éģİåİ»
    0.18
     اÙĦÙħاضÙĬ
    0.18
    è¿ĩå¾Ģ
    0.18
    past
    0.18
    Past
    0.17
    è¿ĩåİ»äºĨ
    0.17
    å¾Ģäºĭ
    0.17
    Activations Density 0.063%

    No Known Activations