© 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. 476
    Prev
    Next
    INDEX
    Explanations

    houses, rooms, accommodation

    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
    æĬķæĶ¾
    -0.28
    åıijæĶ¾
    -0.27
    åĬĽåº¦
    -0.26
    éķĬ
    -0.25
     Polic
    -0.25
    ä½İæĪIJæľ¬
    -0.24
    表æĢģ
    -0.24
    åıĤä¸İèĢħ
    -0.24
    ouri
    -0.23
     Doing
    -0.23
    POSITIVE LOGITS
     interior
    0.45
     interiors
    0.42
     bedrooms
    0.41
    豪å®ħ
    0.37
     bedroom
    0.37
     house
    0.36
     sprawling
    0.35
     spacious
    0.35
     mansion
    0.34
     rooms
    0.34
    Activations Density 0.049%

    No Known Activations