© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 211
    Prev
    Next
    INDEX
    Explanations

    interpretation and ambiguity

    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
     stimulation
    -0.23
    AMS
    -0.22
    IQUE
    -0.22
    壮è§Ĥ
    -0.22
    Und
    -0.21
    scp
    -0.21
    SCP
    -0.21
    guest
    -0.21
    ám
    -0.21
     topped
    -0.21
    POSITIVE LOGITS
    解读
    0.33
     interpretation
    0.32
    çªĦ
    0.30
     interpretations
    0.29
    è§£éĩĬ
    0.29
     Interpret
    0.29
     interpreting
    0.28
     clues
    0.27
     interpret
    0.27
    宽
    0.27
    Activations Density 0.011%

    No Known Activations