© 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. 14124
    Prev
    Next
    INDEX
    Explanations

    claim, claims, claimed

    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
    å¼ĢéŨ
    -0.20
    æĬĵç´§
    -0.20
    æĴŃ
    -0.19
    积èĵĦ
    -0.19
    ä¹Łç®Ĺæĺ¯
    -0.18
    æĪIJé¾Ļ
    -0.18
     gam
    -0.17
     Fuse
    -0.17
    emporary
    -0.17
    åľŁè±ª
    -0.17
    POSITIVE LOGITS
    声称
    0.38
     claim
    0.28
     claimed
    0.28
    èĻļæŀĦ
    0.27
     Claim
    0.27
     claims
    0.27
     Claims
    0.26
    æ¶īå«Į
    0.26
     CLAIM
    0.26
    宣称
    0.25
    Activations Density 0.191%

    No Known Activations