© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    hard and rigid materials

    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
    adow
    -0.19
    è¾į
    -0.19
    StackSize
    -0.18
    iad
    -0.18
     SOC
    -0.18
    è§Ħ模æľĢ大
    -0.18
    .addData
    -0.17
     rum
    -0.17
    aska
    -0.17
    rador
    -0.17
    POSITIVE LOGITS
    硬
    0.29
    -hard
    0.23
    åĿļ硬
    0.21
    æ¢Ĩ
    0.21
    æĸ°éĹ»ç½ij
    0.20
    ä¸į容æĺĵ
    0.20
    æľĢéļ¾
    0.20
     HARD
    0.20
    Hard
    0.19
    对æĬĹ
    0.19
    Activations Density 0.028%

    No Known Activations