© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    pest and pests

    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
    ../
    -0.26
    è¿Ļæĺ¯ä¸Ģç§į
    -0.24
    éļ°
    -0.21
    ãĥ¼ãĥł
    -0.20
    è¿Ļæĺ¯åĽłä¸º
    -0.20
    æı¡ä½ı
    -0.20
    è¿Ļç§įæĸ¹å¼ı
    -0.20
    ENDED
    -0.19
    å¹ħ
    -0.19
    haul
    -0.19
    POSITIVE LOGITS
    ilent
    0.27
    iest
    0.24
    ivirus
    0.22
    ablish
    0.21
     gì
    0.20
    ened
    0.20
    -conscious
    0.20
    ains
    0.20
    lessness
    0.20
    eced
    0.19
    Activations Density 0.005%

    No Known Activations