© 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. 2578
    Prev
    Next
    INDEX
    Explanations

    reap, bask, revel, realizing, benefit, advantages

    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
    eness
    -0.24
    å·¥ä½ľä»»åĬ¡
    -0.22
    olio
    -0.22
     Chronicle
    -0.21
    enal
    -0.21
    æĢ»éĺŁ
    -0.20
     Rena
    -0.20
    .Comp
    -0.20
    ion
    -0.20
    ãģªãģı
    -0.19
    POSITIVE LOGITS
     benefits
    0.35
     benefit
    0.30
    æĶ¶çĽĬ
    0.26
     advantages
    0.25
    benef
    0.25
    èĥľåĪ©
    0.25
    æķĪçĽĬ
    0.24
     consequences
    0.24
    åĪ©çĶ¨
    0.24
    ride
    0.24
    Activations Density 0.016%

    No Known Activations