© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2722
    Prev
    Next
    INDEX
    Explanations

    student-led initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    dez
    -0.25
     toll
    -0.24
    ULE
    -0.23
    _VENDOR
    -0.23
     ÑĢазмеÑĢ
    -0.23
    unden
    -0.22
    empo
    -0.21
    инг
    -0.21
    iner
    -0.21
    distinct
    -0.21
    POSITIVE LOGITS
    å®ŀè®Ń
    0.46
     students
    0.41
    åѦçĶŁçļĦ
    0.40
    åѦçĶŁä»¬
    0.38
    å®ŀä¹ł
    0.38
    å®ŀä¹łçĶŁ
    0.35
     student
    0.35
    åѦçĶŁ
    0.35
    æ¯ķä¸ļ
    0.34
    çļĦåѦçĶŁ
    0.33
    Activations Density 0.056%

    No Known Activations