© 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. 1130
    Prev
    Next
    INDEX
    Explanations

    leaving a position

    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
     REALLY
    -0.22
    æĬĬè¿ĻäºĽ
    -0.21
    theros
    -0.21
     hoodie
    -0.21
     mojo
    -0.21
     Circus
    -0.21
    OLT
    -0.20
    ç¾İåĮĸ
    -0.20
     tÆ°
    -0.20
     peripheral
    -0.20
    POSITIVE LOGITS
    çĤ¹äºĨ
    0.26
    æļ¨
    0.26
    ued
    0.25
    uka
    0.24
     decay
    0.24
    继æī¿
    0.23
    ä»»
    0.23
    edo
    0.23
    upe
    0.22
    olis
    0.22
    Activations Density 0.051%

    No Known Activations