© 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. 450
    Prev
    Next
    INDEX
    Explanations

    names Gregory, Pu

    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
    åį´è¢«
    -0.25
     Crown
    -0.23
    éĢĤ度
    -0.22
    æļijæľŁ
    -0.21
     Sky
    -0.21
    ansk
    -0.21
    èļģ
    -0.21
     crow
    -0.20
    ours
    -0.20
     Spider
    -0.20
    POSITIVE LOGITS
    åīĬ
    0.27
    èĩªå¸¦
    0.23
    .BO
    0.23
     targ
    0.22
    产éĩı
    0.21
    éĢ»
    0.21
    LOPT
    0.21
    éĺ´å½±
    0.21
     advertised
    0.21
    ProductId
    0.20
    Activations Density 1.355%

    No Known Activations