© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    zip code

    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
     getInstance
    -0.22
    èµ¢
    -0.22
    ieren
    -0.21
    utter
    -0.21
    åIJĦåĽ½
    -0.21
     SECRET
    -0.21
    atra
    -0.21
    STANCE
    -0.20
    loadModel
    -0.20
    rium
    -0.20
    POSITIVE LOGITS
    ë²Īíĺ¸
    0.27
    çłģ
    0.24
    .codes
    0.24
     predominantly
    0.23
     codes
    0.23
    isd
    0.22
     code
    0.22
    å±ħæ°ij
    0.22
    å¾Ĺ天
    0.22
    åŃ¥
    0.21
    Activations Density 0.005%

    No Known Activations