© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    Glenn names or glut-biology terms

    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
    ³
    -0.23
    èĩ¼
    -0.22
    ollo
    -0.22
    /place
    -0.20
    ãģıãĤĭ
    -0.20
     slight
    -0.19
    quil
    -0.19
     blouse
    -0.19
    ogan
    -0.18
    strained
    -0.18
    POSITIVE LOGITS
    burgh
    0.25
    -eyed
    0.24
    çĦ¶æĺ¯
    0.21
    ener
    0.21
    gow
    0.21
    rijk
    0.20
    st
    0.20
    bourne
    0.20
    cation
    0.20
    zeitig
    0.20
    Activations Density 0.154%

    No Known Activations