© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    rationality and rationalization

    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
    elts
    -0.22
    elman
    -0.20
     patented
    -0.19
    entifier
    -0.19
    OrCreate
    -0.19
    noop
    -0.18
    å¹´åĪĿ
    -0.18
    å±ħå§Ķä¼ļ
    -0.18
    éĽģ
    -0.18
     Crosby
    -0.18
    POSITIVE LOGITS
    ization
    0.39
    istic
    0.38
    ity
    0.37
    izing
    0.34
    ized
    0.33
    izations
    0.28
    åĮĸçļĦ
    0.28
    izer
    0.27
    ç²¹
    0.27
    ation
    0.27
    Activations Density 0.007%

    No Known Activations