© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1135
    Prev
    Next
    INDEX
    Explanations

    lasting duration

    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
    PX
    -0.21
     lần
    -0.21
    æĻĤåĢĻ
    -0.20
    pta
    -0.20
    Ñģка
    -0.19
     settled
    -0.19
    .nz
    -0.19
    Tri
    -0.19
     Dw
    -0.19
    -most
    -0.18
    POSITIVE LOGITS
    å¤ļä¹ħ
    0.25
    åĴĮåıijå±ķ
    0.25
    ä¸įæĸŃåľ°
    0.24
    ä¸ĭåİ»
    0.23
    ENCY
    0.23
    haft
    0.23
    ently
    0.23
    .Unicode
    0.22
    cales
    0.22
    glass
    0.22
    Activations Density 0.010%

    No Known Activations