© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1250
    Prev
    Next
    INDEX
    Explanations

    pasting text or links

    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
    nt
    -0.23
    ly
    -0.22
    nte
    -0.22
    ners
    -0.21
    lander
    -0.21
    x
    -0.20
     acceso
    -0.20
    PUTE
    -0.19
    liv
    -0.19
     Mesa
    -0.19
    POSITIVE LOGITS
    ../../../
    0.25
    åľ¨ä¸Ģèµ·
    0.23
    iore
    0.22
    iali
    0.21
    åľ¨çĶŁæ´»ä¸Ń
    0.20
    ernes
    0.20
    åŀĭä¼ģä¸ļ
    0.20
    éĵ¯
    0.20
    -worthy
    0.19
    onclick
    0.19
    Activations Density 0.028%

    No Known Activations