© 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. 632
    Prev
    Next
    INDEX
    Explanations

    uppercase characters or words

    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
    branches
    -0.26
    以人为
    -0.23
    ionario
    -0.23
    èIJ½åı¶
    -0.23
    elib
    -0.23
    isode
    -0.23
    Recorder
    -0.22
    çĶ°åĽŃ
    -0.22
    åħĪè¿ĽçļĦ
    -0.22
    OfYear
    -0.21
    POSITIVE LOGITS
     glaring
    0.26
     letterSpacing
    0.26
    eners
    0.25
    sig
    0.24
     emoc
    0.24
    ASCII
    0.24
    æ°ĶåĬ¿
    0.24
     emot
    0.23
    æĢ¥
    0.23
     ascii
    0.23
    Activations Density 0.011%

    No Known Activations