© 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. 2196
    Prev
    Next
    INDEX
    Explanations

    look like a shape

    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
     Sparks
    -0.27
    çķĻå®Ī
    -0.25
    -shared
    -0.24
     privat
    -0.23
    ç»Ī身
    -0.23
    eva
    -0.22
    æ£ĺ
    -0.22
    лей
    -0.22
    æĸ°åĬł
    -0.22
     misunderstand
    -0.22
    POSITIVE LOGITS
    å½¢çĬ¶
    0.40
     shape
    0.36
     shapes
    0.35
    çļĦæ¨¡æł·
    0.35
    -shaped
    0.33
    çļĦæł·åŃIJ
    0.32
    shapes
    0.32
    å¤ĸå½¢
    0.31
    shape
    0.31
    .shapes
    0.30
    Activations Density 0.046%

    No Known Activations