© 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. 12933
    Prev
    Next
    INDEX
    Explanations

    brushing and grooming hair

    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
    alf
    -0.22
     tempor
    -0.20
     water
    -0.19
    æ±Ģ
    -0.19
    桶
    -0.19
    çªij
    -0.19
    ç¥Ĺ
    -0.19
    auce
    -0.19
     Hands
    -0.18
    水墨
    -0.18
    POSITIVE LOGITS
    梳
    0.26
    éķĬ
    0.20
    头åıij
    0.20
    两款
    0.20
    æĶ¶å½ķ
    0.19
    æķıæĦŁ
    0.18
    æ±ĩéĽĨ
    0.18
    ITO
    0.18
    管è¾ĸ
    0.18
     blow
    0.17
    Activations Density 0.014%

    No Known Activations