© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    personal

    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
    æĶ¾è¿ĩ
    -0.22
    大大å°ıå°ı
    -0.22
    (s
    -0.21
    åĪ«äººçļĦ
    -0.21
     divers
    -0.21
    西路
    -0.21
    æĪĺèĥľ
    -0.20
     Pompe
    -0.20
     pieces
    -0.20
    åįģä¸īäºĶ
    -0.20
    POSITIVE LOGITS
     помеÑī
    0.24
    æīŃ
    0.23
    subject
    0.22
    èĢģåĮĸ
    0.22
    _ttl
    0.22
    º«
    0.22
    anium
    0.21
    dit
    0.21
    ì¶ķ
    0.21
    è§Ħæł¼
    0.20
    Activations Density 0.002%

    No Known Activations