© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11799
    Prev
    Next
    INDEX
    Explanations

    accused of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ifest
    -0.20
    èĽĨ
    -0.18
    yer
    -0.18
    ç³ĸå°¿
    -0.17
    į
    -0.17
    uges
    -0.17
    æĸ°å±ĢéĿ¢
    -0.16
    alone
    -0.16
    astr
    -0.16
    çŃĩ
    -0.16
    POSITIVE LOGITS
    ably
    0.22
    /question
    0.18
    ments
    0.17
    æĻ°
    0.16
    人家
    0.16
    ively
    0.15
    emente
    0.15
    éķ¿è¾Ī
    0.15
    sm
    0.15
    sa
    0.15
    Activations Density 0.006%

    No Known Activations