© 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. 2429
    Prev
    Next
    INDEX
    Explanations

    Click Here

    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
    æĸ½å±ķ
    -0.23
    UnderTest
    -0.22
    ÑĢÑı
    -0.22
    .RowStyles
    -0.21
    åģļ大
    -0.21
    Pres
    -0.21
    vil
    -0.21
    åľ°
    -0.21
    就好
    -0.21
     minim
    -0.20
    POSITIVE LOGITS
    å¤įæ´»
    0.29
    æ´»åĬ¨ä¸Ń
    0.24
    éĥ¨åĪĨåĨħ容
    0.23
    http
    0.23
    -elements
    0.22
    夹
    0.22
    agenda
    0.22
    åħ·ä½ĵåĨħ容
    0.22
     Link
    0.22
    å½ĵä½ł
    0.22
    Activations Density 0.084%

    No Known Activations