© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    ecosystem services

    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
    åĿĬ
    -0.28
    /edit
    -0.21
     unconditional
    -0.21
    ä¸ĢæĹı
    -0.21
    /Edit
    -0.21
    ish
    -0.21
    æŀ¶åŃIJ
    -0.20
    ç«ĭå¿Ĺ
    -0.20
    å°º
    -0.20
    etest
    -0.20
    POSITIVE LOGITS
    /environment
    0.27
    åŃ¦å®¶
    0.25
    -wise
    0.24
    æ·±å¤Ħ
    0.23
    -wide
    0.23
    åıijèĤ²
    0.23
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.23
    çĶŁäº§æĢ»åĢ¼
    0.22
    çĶŁæĢģç³»ç»Ł
    0.22
    wide
    0.22
    Activations Density 0.015%

    No Known Activations